commit 9115a10eebd5957235f3b09503fdedc7c8d57b26 Author: ModelHub XC Date: Sat Jun 20 04:43:13 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: utter-project/EuroMoE-2.6B-A0.6B-Instruct-Preview Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c5d6f85 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,52 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text + +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +tokenizer.json filter=lfs diff=lfs merge=lfs -text +tokenizer.model filter=lfs diff=lfs merge=lfs -text +model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..f84dd9f --- /dev/null +++ b/README.md @@ -0,0 +1,118 @@ +--- +license: apache-2.0 +language: +- en +- de +- es +- fr +- it +- pt +- pl +- nl +- tr +- sv +- cs +- el +- hu +- ro +- fi +- uk +- sl +- sk +- da +- lt +- lv +- et +- bg +- 'no' +- ca +- hr +- ga +- mt +- gl +- zh +- ru +- ko +- ja +- ar +- hi +library_name: transformers +base_model: +- utter-project/EuroMoE-2.6B-A0.6B-Preview +--- + +# Model Card for EuroMoE-2.6B-A0.6B-Instruct-Preview + +⚠️ PREVIEW RELEASE: This is a preview version of EuroMoE-2.6B-A0.6B-Instruct-Preview. The model is still under development and may have limitations in performance and stability. Use with caution in production environments. + +This is the model card for EuroMoE-2.6B-A0.6B-Instruct-Preview. You can also check the pre-trained version: [EuroMoE-2.6B-A0.6B-Preview](https://huggingface.co/utter-project/EuroMoE-2.6B-A0.6B-Preview). + +- **Developed by:** Unbabel, Instituto Superior Técnico, Instituto de Telecomunicações, University of Edinburgh, Aveni, University of Paris-Saclay, University of Amsterdam, Naver Labs, Sorbonne Université. +- **Funded by:** European Union. +- **Model type:** A 2.6B parameter multilingual transformer MoE with 0.6B active parameters. +- **Language(s) (NLP):** Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Greek, Hungarian, Irish, Italian, Latvian, Lithuanian, Maltese, Polish, Portuguese, Romanian, Slovak, Slovenian, Spanish, Swedish, Arabic, Catalan, Chinese, Galician, Hindi, Japanese, Korean, Norwegian, Russian, Turkish, and Ukrainian. +- **License:** Apache License 2.0. + +## Model Details + +The EuroLLM project has the goal of creating a suite of LLMs capable of understanding and generating text in all European Union languages as well as some additional relevant languages. +EuroMoE-2.6B-A0.6B is a 22B parameter model trained on 8 trillion tokens divided across the considered languages and several data sources: Web data, parallel data (en-xx and xx-en), and high-quality datasets. +EuroMoE-2.6B-A0.6B-Instruct was further instruction tuned on EuroBlocks, an instruction tuning dataset with focus on general instruction-following and machine translation. + + +### Model Description + +EuroMoE uses a standard MoE Transformer architecture: +- We use grouped query attention (GQA) with 2 key-value heads, since it has been shown to increase speed at inference time while maintaining downstream performance. +- We perform pre-layer normalization, since it improves the training stability, and use the RMSNorm, which is faster. +- We use the SwiGLU activation function, since it has been shown to lead to good results on downstream tasks. +- We use rotary positional embeddings (RoPE) in every layer, since these have been shown to lead to good performances while allowing the extension of the context length. + +For pre-training, we use 512 Nvidia A100 GPUs of the Leonardo supercomputer, training the model with a constant batch size of 4096 sequences, which corresponds to approximately 17 million tokens, using the Adam optimizer, and BF16 precision. +Here is a summary of the model hyper-parameters: +| | | +|--------------------------------------|----------------------| +| Sequence Length | 4,096 | +| Number of Layers | 24 | +| Embedding Size | 1,024 | +| Total/Active experts | 64/8 | +| Expert Hidden Size | 512 | +| Number of Heads | 8 | +| Number of KV Heads (GQA) | 2 | +| Activation Function | SwiGLU | +| Position Encodings | RoPE (\Theta=500,000) | +| Layer Norm | RMSNorm | +| Tied Embeddings | Yes | +| Embedding Parameters | 0.13B | +| LM Head Parameters | 0.13B | +| Active Non-embedding Parameters | 0.34B | +| Total Non-embedding Parameters | 2.35B | +| Active Parameters | 0.6B | +| Total Parameters | 2.61B | + +## Run the model + + from transformers import AutoModelForCausalLM, AutoTokenizer + + model_id = "utter-project/EuroMoE-2.6B-A0.6B-Instruct-Preview" + tokenizer = AutoTokenizer.from_pretrained(model_id) + model = AutoModelForCausalLM.from_pretrained(model_id) + + messages = [ + { + "role": "system", + "content": "You are EuroLLM --- an AI assistant specialized in European languages that provides safe, educational and helpful answers.", + }, + { + "role": "user", "content": "What is the capital of Portugal? How would you describe it?" + }, + ] + + inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt") + outputs = model.generate(inputs, max_new_tokens=1024) + print(tokenizer.decode(outputs[0], skip_special_tokens=True)) + + +## Bias, Risks, and Limitations + +EuroMoE-2.6B-A0.6B-Instruct-Preview has not been aligned to human preferences, so the model may generate problematic outputs (e.g., hallucinations, harmful content, or false statements). \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..b560ee7 --- /dev/null +++ b/config.json @@ -0,0 +1,32 @@ +{ + "_name_or_path": "/mnt/cephfs-nvme/nunomg/axolotl/sft_ckpts/eurollm/EuroBlocks-500M-2.5B-MoE-200525-chatml-after-anneal", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 4, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 512, + "max_position_embeddings": 4096, + "model_type": "mixtral", + "num_attention_heads": 8, + "num_experts_per_tok": 8, + "num_hidden_layers": 24, + "num_key_value_heads": 2, + "num_local_experts": 64, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 500000, + "router_aux_loss_coef": 0.01, + "router_jitter_noise": 0.0, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.46.1", + "use_cache": false, + "vocab_size": 128000 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..95f23b4 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "do_sample": true, + "eos_token_id": 2, + "transformers_version": "4.46.1" +} diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..f67059c --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dffaff23a9e5e58a8dd19745cbdcf22095f4e7f28d6183d08b009221ab22dc5e +size 5000160568 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..33df1d2 --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f23d9076af7abad027cd092a9a19c140dd6fd9cfb0315c1612f7c400b171f03 +size 223515752 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..cf3d827 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,4785 @@ +{ + "metadata": { + "total_size": 5223057408 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.10.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.11.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.12.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.13.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.14.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.15.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.16.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.17.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", + "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.18.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", + "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.19.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", + "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.20.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", + "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.21.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", + "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.58.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.59.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.59.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.59.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.60.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.60.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.60.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.61.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.61.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.61.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.62.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.62.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.62.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.63.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.63.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.63.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.22.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.10.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.10.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.10.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.11.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.11.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.11.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.12.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.12.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.12.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.13.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.13.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.13.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.14.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.14.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.14.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.15.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.15.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.15.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.16.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.16.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.16.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.17.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.17.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.17.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.18.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.18.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.18.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.19.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.19.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.19.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.20.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.20.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.20.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.21.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.21.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.21.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.22.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.22.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.22.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.23.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.23.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.23.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.24.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.24.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.24.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.25.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.25.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.25.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.26.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.26.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.26.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.27.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.27.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.27.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.28.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.28.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.28.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.29.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.29.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.29.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.30.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.30.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.30.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.31.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.31.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.31.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.32.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.32.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.32.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.33.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.33.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.33.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.34.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.34.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.34.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.35.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.35.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.35.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.36.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.36.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.36.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.37.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.37.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.37.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.38.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.38.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.38.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.39.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.39.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.39.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.40.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.40.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.40.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.41.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.41.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.41.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.42.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.42.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.42.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.43.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.43.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.43.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.44.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.44.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.44.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.45.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.45.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.45.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.46.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.46.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.46.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.47.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.47.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.47.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.48.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.48.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.48.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.49.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.49.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.49.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.50.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.50.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.50.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.51.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.51.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.51.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.52.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.52.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.52.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.53.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.53.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.53.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.54.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.54.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.54.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.55.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.55.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.55.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.56.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.56.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.56.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.57.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.57.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.57.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.58.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.58.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.58.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.59.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.59.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.59.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.60.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.60.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.60.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.61.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.61.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.61.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.62.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.62.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.62.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.63.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.63.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.63.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.8.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.8.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.8.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.9.w1.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.9.w2.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.experts.9.w3.weight": "model-00002-of-00002.safetensors", + "model.layers.23.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.6.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.7.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.8.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", + "model.layers.9.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.norm.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..d555d77 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,30 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..2d619c7 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6e4810e827e4ffcd735429d19d585326bb4efb31e921cb870ecefc4c1fa16e3 +size 15783507 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..062965b --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42957aec88804838805b335da1bbcce9d116024a20c6c4b56757648b9e348254 +size 2408875 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..d04165a --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2108 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "5": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "13": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "14": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "15": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "16": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "17": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "18": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "19": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "20": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "21": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "22": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "23": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "24": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "25": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "26": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "27": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "28": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "29": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "30": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "31": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "32": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "33": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "34": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "35": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "36": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "37": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "38": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "39": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "40": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "41": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "42": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "43": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "44": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "45": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "46": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "47": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "48": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "49": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "50": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "51": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "52": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "53": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "54": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "55": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "56": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "57": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "58": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "59": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "60": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "62": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "63": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "64": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "65": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "66": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "67": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "68": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "69": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "70": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "71": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "72": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "73": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "74": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "75": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "76": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "77": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "78": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "79": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "80": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "81": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "82": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "83": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "84": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "85": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "86": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "87": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "88": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "89": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "90": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "91": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "92": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "93": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "94": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "95": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "96": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "97": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "98": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "99": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "101": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "102": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "103": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "104": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "108": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "135": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "136": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "137": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "138": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "139": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "140": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "141": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "142": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "143": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "144": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "145": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "146": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "147": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "148": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "149": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "150": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "152": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "153": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "155": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "156": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "157": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "158": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "159": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "160": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "161": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "162": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "163": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "164": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "165": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "166": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "167": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "168": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "169": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "170": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "171": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "172": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "173": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "174": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "175": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "176": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "177": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "178": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "179": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "180": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "181": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "182": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "183": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "184": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "185": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "186": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "187": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "188": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "189": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "190": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "191": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "192": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "193": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "194": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "195": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "196": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "197": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "198": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "199": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "200": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "201": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "202": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "203": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "204": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "205": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "206": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "207": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "208": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "209": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "210": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "211": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "212": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "213": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "214": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "215": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "216": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "217": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "218": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "219": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "220": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "221": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "222": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "223": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "224": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "225": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "226": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "227": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "228": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "229": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "230": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "231": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "232": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "233": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "234": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "235": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "236": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "237": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "238": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "239": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "240": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "241": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "242": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "243": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "244": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "245": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "246": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "247": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "248": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "249": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "250": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "251": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "252": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "253": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "254": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "256": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "257": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "258": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "259": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "260": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "", + "chat_template": "{% for message in messages %}{% if message['role'] == 'assistant' %}{% set role = 'assistant' %}{% else %}{% set role = message['role'] %}{% endif %}<|im_start|>{{ role }}\n{{ message['content'] | trim }}<|im_end|>\n{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant\n'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}