commit 93bf483f83135b70778c478be64a22dc4fb64ef0 Author: ModelHub XC Date: Tue Jul 7 19:28:13 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: MaziyarPanahi/Qwen1.5-MoE-A2.7B-Wikihow Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6e6dba0 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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 +*.model 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 + +model-00005-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00002-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +model-00006-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +merges.txt 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..aee9f21 --- /dev/null +++ b/README.md @@ -0,0 +1,172 @@ +--- +license: apache-2.0 +library_name: transformers +tags: +- generated_from_trainer +- fine-tuned +- wikihow +- cosmopedia +- qwen +- moe +base_model: Qwen/Qwen1.5-MoE-A2.7B +datasets: +- HuggingFaceTB/cosmopedia +pipeline_tag: text-generation +model-index: +- name: models/Qwen1.5-MoE-A2.7B-Wikihow + results: [] +--- + +# models/Qwen1.5-MoE-A2.7B-Wikihow + +This model is a fine-tuned version of [Qwen/Qwen1.5-MoE-A2.7B](https://huggingface.co/Qwen/Qwen1.5-MoE-A2.7B) on the [HuggingFaceTB/cosmopedia](https://huggingface.co/datasets/HuggingFaceTB/cosmopedia) dataset. + + +## How to use it + +```python +# Use a pipeline as a high-level helper +from transformers import pipeline + +pipe = pipeline("text-generation", model="MaziyarPanahi/Qwen1.5-MoE-A2.7B-Wikihow") +``` + +```python +# Load model directly +from transformers import AutoTokenizer, AutoModelForCausalLM + +tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/Qwen1.5-MoE-A2.7B-Wikihow") +model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/Qwen1.5-MoE-A2.7B-Wikihow") +``` + + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 0.0002 +- train_batch_size: 2 +- eval_batch_size: 2 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 4 +- gradient_accumulation_steps: 4 +- total_train_batch_size: 32 +- total_eval_batch_size: 8 +- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 +- lr_scheduler_type: cosine +- lr_scheduler_warmup_steps: 10 +- num_epochs: 1 + +### Training results + + + +[Built with Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) +
See axolotl config + +axolotl version: `0.4.0` +```yaml +base_model: Qwen/Qwen1.5-MoE-A2.7B +trust_remote_code: true + +load_in_8bit: false +load_in_4bit: true +strict: false + +# hub_model_id: MaziyarPanahi/Qwen1.5-MoE-A2.7B-Wikihow +# hf_use_auth_token: true + +chat_template: chatml + +datasets: + - path: HuggingFaceTB/cosmopedia + name: wikihow + type: + system_prompt: "" + field_instruction: prompt + field_output: text + format: "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n" + no_input_format: "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n" + +dataset_prepared_path: +val_set_size: 0.0 +output_dir: ./models/Qwen1.5-MoE-A2.7B-Wikihow + +sequence_len: 2048 +sample_packing: false +pad_to_sequence_len: false + +adapter: lora +lora_model_dir: +lora_r: 32 +lora_alpha: 16 +lora_dropout: 0.05 +lora_target_linear: true +lora_fan_in_fan_out: + +wandb_project: +wandb_entity: +wandb_watch: +wandb_name: +wandb_log_model: + +gradient_accumulation_steps: 4 +micro_batch_size: 2 +num_epochs: 1 +optimizer: paged_adamw_8bit +lr_scheduler: cosine +learning_rate: 0.0002 + +train_on_inputs: false +group_by_length: false +bf16: auto +fp16: +tf32: true + +gradient_checkpointing: true +gradient_checkpointing_kwargs: + use_reentrant: false +early_stopping_patience: +resume_from_checkpoint: +local_rank: +logging_steps: 1 +xformers_attention: +flash_attention: true + +warmup_steps: 10 +evals_per_epoch: 4 +saves_per_epoch: 1 +debug: +deepspeed: +weight_decay: 0.0 +fsdp: +fsdp_config: +special_tokens: +``` + +

+ + +### Framework versions + +- PEFT 0.10.0 +- Transformers 4.40.0.dev0 +- Pytorch 2.2.0+cu121 +- Datasets 2.18.0 +- Tokenizers 0.15.2 +# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) +Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_MaziyarPanahi__Qwen1.5-MoE-A2.7B-Wikihow) + +| Metric |Value| +|-------------------|----:| +|Avg. |11.43| +|IFEval (0-Shot) |29.54| +|BBH (3-Shot) |15.47| +|MATH Lvl 5 (4-Shot)| 2.87| +|GPQA (0-shot) | 3.36| +|MuSR (0-shot) | 2.01| +|MMLU-PRO (5-shot) |15.34| + diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..409be9f --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,5 @@ +{ + "<|endoftext|>": 151643, + "<|im_end|>": 151645, + "<|im_start|>": 151644 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..581f609 --- /dev/null +++ b/config.json @@ -0,0 +1,35 @@ +{ + "_name_or_path": "Qwen/Qwen1.5-MoE-A2.7B", + "architectures": [ + "Qwen2MoeForCausalLM" + ], + "attention_dropout": 0.0, + "decoder_sparse_step": 1, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 5632, + "max_position_embeddings": 8192, + "max_window_layers": 21, + "model_type": "qwen2_moe", + "moe_intermediate_size": 1408, + "norm_topk_prob": false, + "num_attention_heads": 16, + "num_experts": 60, + "num_experts_per_tok": 4, + "num_hidden_layers": 24, + "num_key_value_heads": 16, + "output_router_logits": false, + "rms_norm_eps": 1e-06, + "rope_theta": 1000000.0, + "router_aux_loss_coef": 0.001, + "shared_expert_intermediate_size": 5632, + "sliding_window": 32768, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.40.0.dev0", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} 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..36bf3e9 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,10 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "transformers_version": "4.40.0.dev0" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00006.safetensors b/model-00001-of-00006.safetensors new file mode 100644 index 0000000..f948d96 --- /dev/null +++ b/model-00001-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76562721784f58a45a20cccad3af1d5ff63fa82ba31c5d7db0004841b3231554 +size 4996577736 diff --git a/model-00002-of-00006.safetensors b/model-00002-of-00006.safetensors new file mode 100644 index 0000000..b30f400 --- /dev/null +++ b/model-00002-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e148afabbabd269f75c62745496d7f92214245a18c521085bd88e8f7a2201d66 +size 4996347752 diff --git a/model-00003-of-00006.safetensors b/model-00003-of-00006.safetensors new file mode 100644 index 0000000..15d96b3 --- /dev/null +++ b/model-00003-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa046d903e6f7e00349f37c7f4d3be973ef532b9a30ff8326dcd90ad903be859 +size 4997127120 diff --git a/model-00004-of-00006.safetensors b/model-00004-of-00006.safetensors new file mode 100644 index 0000000..5b1faba --- /dev/null +++ b/model-00004-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90fa074266891c2073d76e55c9260ed8581c6b6556399bbe7762a799541f5e62 +size 4985592520 diff --git a/model-00005-of-00006.safetensors b/model-00005-of-00006.safetensors new file mode 100644 index 0000000..34c16d7 --- /dev/null +++ b/model-00005-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f13fa9c0f94349772b2a571a74674138e19ddda0b8c4fd329e9c088aa8d8e972 +size 4996348976 diff --git a/model-00006-of-00006.safetensors b/model-00006-of-00006.safetensors new file mode 100644 index 0000000..13f3c70 --- /dev/null +++ b/model-00006-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1350dba4969cc71025bbd13d4270ba8554206e719987216033bf1d9ea690ff86 +size 3660151400 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..2b3dce7 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,4666 @@ +{ + "metadata": { + "total_size": 28631568384 + }, + "weight_map": { + "lm_head.weight": "model-00006-of-00006.safetensors", + "model.embed_tokens.weight": "model-00001-of-00006.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.0.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.0.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.0.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.1.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.1.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.1.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.10.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.10.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.10.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.11.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.11.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.11.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.12.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.12.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.12.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.13.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.13.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.13.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.14.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.14.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.14.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.15.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.15.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.15.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.16.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.16.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.16.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.17.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.17.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.17.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.18.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.18.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.18.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.19.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.19.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.19.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.2.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.2.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.2.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.20.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.20.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.20.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.21.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.21.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.21.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.22.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.22.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.22.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.23.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.23.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.23.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.24.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.24.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.24.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.25.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.25.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.25.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.26.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.26.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.26.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.27.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.27.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.27.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.28.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.28.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.28.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.29.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.29.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.29.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.3.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.3.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.3.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.30.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.30.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.30.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.31.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.31.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.31.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.32.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.32.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.32.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.33.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.33.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.33.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.34.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.34.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.34.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.35.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.35.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.35.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.36.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.36.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.36.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.37.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.37.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.37.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.38.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.38.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.38.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.39.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.39.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.39.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.4.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.4.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.4.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.40.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.40.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.40.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.41.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.41.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.41.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.42.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.42.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.42.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.43.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.43.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.43.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.44.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.44.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.44.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.45.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.45.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.45.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.46.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.46.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.46.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.47.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.47.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.47.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.48.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.48.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.48.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.49.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.49.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.49.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.5.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.5.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.5.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.50.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.50.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.50.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.51.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.51.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.51.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.52.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.52.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.52.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.53.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.53.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.53.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.54.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.54.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.54.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.55.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.55.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.55.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.56.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.56.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.56.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.57.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.57.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.57.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.58.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.58.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.58.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.59.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.59.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.59.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.6.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.6.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.6.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.7.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.7.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.7.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.8.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.8.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.8.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.9.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.9.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.experts.9.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.gate.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.shared_expert.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.shared_expert.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.shared_expert_gate.weight": "model-00001-of-00006.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.0.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.0.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.1.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.1.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.10.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.10.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.10.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.11.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.11.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.11.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.12.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.12.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.12.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.13.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.13.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.13.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.14.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.14.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.14.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.15.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.15.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.15.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.16.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.16.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.16.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.17.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.17.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.17.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.18.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.18.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.18.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.19.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.19.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.19.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.2.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.2.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.20.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.20.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.20.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.21.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.21.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.21.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.22.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.22.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.22.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.23.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.23.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.23.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.24.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.24.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.24.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.25.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.25.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.25.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.26.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.26.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.26.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.27.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.27.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.27.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.28.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.28.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.28.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.29.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.29.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.29.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.3.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.3.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.30.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.30.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.30.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.31.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.31.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.31.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.32.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.32.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.32.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.33.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.33.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.33.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.34.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.34.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.34.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.35.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.35.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.35.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.36.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.36.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.36.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.37.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.37.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.37.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.38.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.38.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.38.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.39.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.39.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.39.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.4.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.4.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.4.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.40.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.40.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.40.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.41.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.41.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.41.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.42.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.42.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.42.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.43.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.43.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.43.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.44.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.44.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.44.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.45.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.45.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.45.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.46.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.46.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.46.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.47.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.47.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.47.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.48.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.48.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.48.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.49.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.49.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.49.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.5.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.5.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.5.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.50.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.50.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.50.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.51.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.51.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.51.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.52.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.52.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.52.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.53.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.53.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.53.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.54.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.54.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.54.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.55.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.55.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.55.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.56.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.56.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.56.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.57.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.57.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.57.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.58.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.58.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.58.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.59.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.59.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.59.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.6.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.6.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.6.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.7.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.7.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.7.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.8.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.8.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.8.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.9.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.9.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.experts.9.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.gate.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.shared_expert.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.shared_expert.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.shared_expert_gate.weight": "model-00001-of-00006.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.0.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.0.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.1.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.1.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.10.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.10.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.10.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.11.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.11.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.11.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.12.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.12.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.12.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.13.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.13.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.13.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.14.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.14.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.14.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.15.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.15.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.15.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.16.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.16.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.16.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.17.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.17.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.17.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.18.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.18.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.18.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.19.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.19.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.19.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.2.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.2.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.20.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.20.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.20.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.21.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.21.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.21.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.22.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.22.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.22.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.23.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.23.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.23.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.24.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.24.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.24.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.25.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.25.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.25.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.26.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.26.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.26.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.27.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.27.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.27.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.28.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.28.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.28.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.29.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.29.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.29.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.3.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.3.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.30.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.30.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.30.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.31.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.31.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.31.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.32.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.32.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.32.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.33.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.33.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.33.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.34.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.34.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.34.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.35.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.35.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.35.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.36.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.36.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.36.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.37.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.37.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.37.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.38.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.38.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.38.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.39.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.39.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.39.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.4.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.4.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.40.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.40.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.40.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.41.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.41.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.41.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.42.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.42.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.42.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.43.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.43.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.43.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.44.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.44.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.44.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.45.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.45.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.45.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.46.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.46.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.46.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.47.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.47.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.47.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.48.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.48.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.48.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.49.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.49.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.49.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.5.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.5.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.5.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.50.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.50.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.50.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.51.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.51.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.51.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.52.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.52.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.52.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.53.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.53.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.53.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.54.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.54.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.54.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.55.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.55.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.55.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.56.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.56.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.56.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.57.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.57.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.57.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.58.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.58.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.58.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.59.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.59.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.59.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.6.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.6.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.6.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.7.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.7.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.7.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.8.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.8.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.8.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.9.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.9.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.experts.9.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.gate.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.shared_expert.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.shared_expert.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.mlp.shared_expert_gate.weight": "model-00003-of-00006.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.0.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.0.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.1.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.1.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.10.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.10.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.10.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.11.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.11.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.11.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.12.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.12.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.12.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.13.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.13.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.13.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.14.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.14.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.14.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.15.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.15.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.15.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.16.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.16.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.16.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.17.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.17.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.17.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.18.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.18.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.18.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.19.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.19.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.19.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.2.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.2.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.20.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.20.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.20.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.21.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.21.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.21.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.22.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.22.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.22.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.23.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.23.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.23.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.24.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.24.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.24.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.25.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.25.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.25.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.26.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.26.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.26.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.27.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.27.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.27.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.28.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.28.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.28.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.29.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.29.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.29.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.3.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.3.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.30.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.30.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.30.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.31.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.31.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.31.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.32.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.32.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.32.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.33.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.33.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.33.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.34.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.34.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.34.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.35.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.35.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.35.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.36.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.36.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.36.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.37.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.37.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.37.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.38.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.38.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.38.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.39.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.39.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.39.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.4.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.4.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.40.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.40.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.40.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.41.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.41.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.41.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.42.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.42.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.42.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.43.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.43.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.43.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.44.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.44.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.44.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.45.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.45.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.45.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.46.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.46.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.46.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.47.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.47.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.47.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.48.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.48.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.48.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.49.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.49.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.49.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.5.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.5.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.50.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.50.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.50.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.51.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.51.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.51.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.52.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.52.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.52.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.53.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.53.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.53.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.54.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.54.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.54.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.55.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.55.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.55.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.56.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.56.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.56.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.57.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.57.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.57.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.58.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.58.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.58.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.59.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.59.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.59.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.6.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.6.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.7.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.7.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.8.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.8.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.8.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.9.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.9.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.experts.9.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.gate.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.shared_expert.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.shared_expert.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.mlp.shared_expert_gate.weight": "model-00003-of-00006.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.0.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.0.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.1.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.1.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.10.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.10.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.10.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.11.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.11.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.11.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.12.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.12.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.12.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.13.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.13.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.13.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.14.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.14.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.14.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.15.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.15.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.15.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.16.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.16.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.16.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.17.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.17.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.17.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.18.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.18.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.18.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.19.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.19.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.19.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.2.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.2.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.20.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.20.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.20.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.21.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.21.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.21.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.22.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.22.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.22.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.23.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.23.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.23.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.24.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.24.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.24.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.25.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.25.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.25.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.26.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.26.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.26.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.27.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.27.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.27.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.28.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.28.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.28.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.29.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.29.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.29.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.3.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.3.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.30.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.30.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.30.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.31.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.31.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.31.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.32.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.32.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.32.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.33.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.33.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.33.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.34.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.34.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.34.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.35.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.35.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.35.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.36.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.36.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.36.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.37.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.37.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.37.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.38.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.38.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.38.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.39.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.39.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.39.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.4.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.4.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.4.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.40.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.40.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.40.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.41.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.41.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.41.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.42.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.42.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.42.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.43.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.43.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.43.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.44.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.44.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.44.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.45.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.45.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.45.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.46.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.46.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.46.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.47.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.47.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.47.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.48.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.48.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.48.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.49.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.49.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.49.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.5.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.5.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.5.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.50.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.50.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.50.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.51.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.51.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.51.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.52.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.52.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.52.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.53.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.53.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.53.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.54.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.54.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.54.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.55.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.55.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.55.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.56.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.56.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.56.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.57.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.57.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.57.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.58.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.58.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.58.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.59.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.59.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.59.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.experts.6.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.6.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.6.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.7.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.7.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.7.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.8.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.8.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.8.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.9.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.9.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.experts.9.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.gate.weight": "model-00003-of-00006.safetensors", + "model.layers.12.mlp.shared_expert.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.shared_expert.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.12.mlp.shared_expert_gate.weight": "model-00004-of-00006.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.13.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.0.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.0.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.1.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.1.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.10.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.10.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.10.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.11.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.11.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.11.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.12.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.12.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.12.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.13.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.13.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.13.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.14.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.14.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.14.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.15.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.15.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.15.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.16.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.16.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.16.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.17.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.17.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.17.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.18.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.18.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.18.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.19.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.19.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.19.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.2.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.2.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.20.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.20.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.20.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.21.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.21.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.21.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.22.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.22.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.22.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.23.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.23.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.23.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.24.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.24.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.24.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.25.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.25.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.25.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.26.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.26.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.26.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.27.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.27.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.27.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.28.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.28.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.28.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.29.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.29.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.29.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.3.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.3.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.30.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.30.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.30.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.31.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.31.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.31.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.32.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.32.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.32.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.33.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.33.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.33.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.34.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.34.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.34.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.35.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.35.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.35.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.36.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.36.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.36.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.37.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.37.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.37.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.38.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.38.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.38.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.39.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.39.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.39.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.4.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.4.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.4.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.40.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.40.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.40.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.41.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.41.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.41.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.42.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.42.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.42.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.43.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.43.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.43.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.44.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.44.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.44.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.45.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.45.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.45.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.46.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.46.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.46.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.47.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.47.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.47.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.48.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.48.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.48.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.49.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.49.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.49.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.5.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.5.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.5.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.50.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.50.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.50.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.51.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.51.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.51.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.52.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.52.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.52.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.53.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.53.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.53.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.54.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.54.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.54.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.55.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.55.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.55.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.56.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.56.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.56.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.57.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.57.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.57.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.58.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.58.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.58.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.59.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.59.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.59.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.6.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.6.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.6.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.7.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.7.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.7.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.8.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.8.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.8.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.9.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.9.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.experts.9.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.gate.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.shared_expert.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.shared_expert.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.mlp.shared_expert_gate.weight": "model-00004-of-00006.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.0.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.0.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.1.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.1.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.10.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.10.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.10.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.11.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.11.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.11.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.12.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.12.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.12.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.13.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.13.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.13.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.14.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.14.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.14.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.15.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.15.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.15.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.16.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.16.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.16.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.17.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.17.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.17.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.18.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.18.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.18.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.19.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.19.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.19.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.2.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.2.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.20.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.20.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.20.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.21.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.21.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.21.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.22.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.22.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.22.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.23.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.23.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.23.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.24.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.24.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.24.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.25.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.25.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.25.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.26.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.26.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.26.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.27.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.27.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.27.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.28.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.28.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.28.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.29.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.29.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.29.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.3.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.3.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.30.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.30.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.30.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.31.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.31.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.31.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.32.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.32.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.32.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.33.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.33.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.33.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.34.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.34.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.34.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.35.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.35.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.35.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.36.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.36.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.36.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.37.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.37.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.37.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.38.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.38.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.38.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.39.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.39.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.39.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.4.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.4.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.4.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.40.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.40.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.40.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.41.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.41.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.41.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.42.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.42.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.42.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.43.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.43.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.43.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.44.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.44.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.44.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.45.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.45.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.45.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.46.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.46.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.46.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.47.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.47.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.47.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.48.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.48.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.48.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.49.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.49.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.49.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.5.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.5.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.5.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.50.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.50.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.50.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.51.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.51.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.51.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.52.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.52.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.52.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.53.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.53.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.53.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.54.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.54.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.54.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.55.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.55.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.55.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.56.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.56.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.56.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.57.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.57.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.57.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.58.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.58.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.58.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.59.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.59.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.59.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.6.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.6.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.6.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.7.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.7.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.7.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.8.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.8.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.8.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.9.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.9.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.experts.9.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.gate.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.shared_expert.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.shared_expert.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.mlp.shared_expert_gate.weight": "model-00004-of-00006.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.0.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.0.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.1.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.1.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.10.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.10.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.10.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.11.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.11.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.11.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.12.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.12.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.12.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.13.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.13.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.13.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.14.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.14.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.14.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.15.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.15.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.15.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.16.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.16.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.16.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.17.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.17.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.17.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.18.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.18.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.18.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.19.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.19.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.19.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.2.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.2.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.20.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.20.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.20.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.21.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.21.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.21.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.22.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.22.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.22.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.23.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.23.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.23.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.24.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.24.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.24.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.25.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.25.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.25.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.26.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.26.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.26.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.27.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.27.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.27.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.28.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.28.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.28.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.29.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.29.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.29.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.3.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.3.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.30.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.30.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.30.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.31.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.31.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.31.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.32.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.32.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.32.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.33.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.33.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.33.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.34.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.34.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.34.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.35.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.35.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.35.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.36.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.36.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.36.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.37.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.37.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.37.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.38.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.38.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.38.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.39.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.39.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.39.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.4.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.4.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.40.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.40.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.40.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.41.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.41.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.41.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.42.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.42.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.42.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.43.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.43.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.43.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.44.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.44.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.44.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.45.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.45.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.45.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.46.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.46.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.46.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.47.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.47.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.47.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.48.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.48.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.48.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.49.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.49.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.49.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.5.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.5.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.5.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.50.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.50.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.50.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.51.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.51.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.51.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.52.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.52.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.52.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.53.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.53.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.53.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.54.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.54.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.54.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.55.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.55.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.55.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.56.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.56.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.56.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.57.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.57.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.57.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.58.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.58.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.58.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.59.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.59.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.59.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.6.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.6.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.6.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.7.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.7.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.7.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.8.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.8.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.8.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.9.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.9.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.experts.9.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.gate.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.shared_expert.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.shared_expert.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.mlp.shared_expert_gate.weight": "model-00004-of-00006.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.16.mlp.experts.0.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.0.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.1.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.1.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.10.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.10.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.10.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.11.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.11.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.11.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.12.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.12.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.12.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.13.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.13.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.13.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.14.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.14.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.14.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.15.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.15.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.15.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.16.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.16.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.16.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.17.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.17.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.17.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.18.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.18.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.18.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.19.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.19.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.19.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.2.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.2.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.20.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.20.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.20.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.21.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.21.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.21.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.22.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.22.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.22.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.23.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.23.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.23.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.24.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.24.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.24.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.25.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.25.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.25.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.26.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.26.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.26.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.27.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.27.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.27.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.28.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.28.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.28.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.29.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.29.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.29.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.3.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.3.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.30.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.30.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.30.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.31.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.31.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.31.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.32.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.32.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.32.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.33.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.33.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.33.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.34.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.34.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.34.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.35.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.35.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.35.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.36.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.36.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.36.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.37.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.37.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.37.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.38.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.38.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.38.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.39.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.39.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.39.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.4.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.4.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.4.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.40.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.40.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.40.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.41.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.41.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.41.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.42.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.42.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.42.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.43.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.43.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.43.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.44.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.44.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.44.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.45.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.45.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.45.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.46.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.46.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.46.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.47.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.47.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.47.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.48.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.48.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.48.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.49.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.49.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.49.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.5.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.5.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.5.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.50.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.50.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.50.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.51.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.51.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.51.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.52.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.52.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.52.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.53.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.53.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.53.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.54.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.54.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.54.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.55.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.55.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.55.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.56.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.56.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.56.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.57.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.57.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.57.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.58.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.58.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.58.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.59.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.59.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.59.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.6.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.6.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.6.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.7.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.7.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.7.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.8.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.8.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.8.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.9.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.9.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.experts.9.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.gate.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.shared_expert.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.mlp.shared_expert.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.16.mlp.shared_expert_gate.weight": "model-00005-of-00006.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.17.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.0.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.0.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.1.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.1.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.10.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.10.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.10.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.11.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.11.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.11.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.12.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.12.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.12.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.13.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.13.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.13.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.14.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.14.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.14.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.15.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.15.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.15.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.16.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.16.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.16.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.17.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.17.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.17.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.18.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.18.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.18.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.19.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.19.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.19.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.2.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.2.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.20.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.20.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.20.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.21.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.21.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.21.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.22.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.22.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.22.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.23.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.23.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.23.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.24.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.24.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.24.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.25.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.25.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.25.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.26.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.26.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.26.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.27.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.27.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.27.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.28.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.28.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.28.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.29.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.29.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.29.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.3.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.3.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.30.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.30.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.30.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.31.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.31.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.31.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.32.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.32.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.32.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.33.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.33.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.33.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.34.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.34.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.34.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.35.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.35.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.35.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.36.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.36.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.36.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.37.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.37.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.37.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.38.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.38.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.38.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.39.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.39.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.39.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.4.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.4.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.4.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.40.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.40.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.40.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.41.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.41.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.41.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.42.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.42.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.42.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.43.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.43.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.43.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.44.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.44.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.44.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.45.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.45.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.45.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.46.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.46.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.46.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.47.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.47.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.47.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.48.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.48.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.48.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.49.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.49.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.49.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.5.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.5.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.5.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.50.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.50.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.50.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.51.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.51.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.51.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.52.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.52.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.52.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.53.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.53.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.53.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.54.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.54.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.54.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.55.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.55.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.55.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.56.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.56.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.56.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.57.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.57.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.57.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.58.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.58.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.58.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.59.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.59.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.59.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.6.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.6.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.6.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.7.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.7.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.7.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.8.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.8.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.8.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.9.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.9.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.experts.9.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.gate.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.shared_expert.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.shared_expert.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.mlp.shared_expert_gate.weight": "model-00005-of-00006.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.0.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.0.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.1.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.1.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.10.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.10.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.10.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.11.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.11.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.11.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.12.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.12.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.12.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.13.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.13.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.13.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.14.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.14.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.14.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.15.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.15.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.15.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.16.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.16.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.16.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.17.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.17.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.17.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.18.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.18.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.18.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.19.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.19.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.19.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.2.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.2.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.20.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.20.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.20.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.21.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.21.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.21.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.22.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.22.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.22.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.23.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.23.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.23.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.24.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.24.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.24.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.25.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.25.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.25.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.26.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.26.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.26.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.27.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.27.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.27.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.28.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.28.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.28.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.29.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.29.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.29.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.3.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.3.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.30.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.30.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.30.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.31.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.31.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.31.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.32.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.32.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.32.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.33.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.33.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.33.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.34.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.34.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.34.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.35.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.35.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.35.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.36.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.36.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.36.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.37.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.37.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.37.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.38.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.38.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.38.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.39.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.39.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.39.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.4.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.4.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.4.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.40.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.40.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.40.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.41.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.41.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.41.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.42.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.42.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.42.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.43.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.43.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.43.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.44.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.44.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.44.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.45.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.45.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.45.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.46.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.46.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.46.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.47.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.47.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.47.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.48.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.48.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.48.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.49.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.49.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.49.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.5.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.5.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.5.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.50.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.50.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.50.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.51.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.51.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.51.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.52.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.52.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.52.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.53.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.53.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.53.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.54.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.54.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.54.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.55.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.55.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.55.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.56.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.56.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.56.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.57.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.57.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.57.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.58.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.58.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.58.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.59.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.59.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.59.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.6.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.6.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.6.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.7.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.7.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.7.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.8.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.8.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.8.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.9.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.9.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.experts.9.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.gate.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.shared_expert.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.shared_expert.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.mlp.shared_expert_gate.weight": "model-00005-of-00006.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.0.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.0.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.1.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.1.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.10.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.10.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.10.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.11.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.11.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.11.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.12.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.12.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.12.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.13.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.13.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.13.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.14.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.14.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.14.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.15.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.15.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.15.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.16.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.16.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.16.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.17.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.17.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.17.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.18.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.18.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.18.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.19.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.19.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.19.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.2.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.2.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.20.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.20.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.20.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.21.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.21.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.21.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.22.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.22.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.22.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.23.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.23.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.23.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.24.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.24.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.24.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.25.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.25.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.25.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.26.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.26.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.26.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.27.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.27.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.27.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.28.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.28.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.28.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.29.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.29.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.29.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.3.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.3.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.30.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.30.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.30.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.31.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.31.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.31.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.32.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.32.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.32.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.33.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.33.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.33.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.34.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.34.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.34.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.35.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.35.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.35.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.36.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.36.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.36.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.37.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.37.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.37.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.38.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.38.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.38.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.39.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.39.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.39.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.4.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.4.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.40.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.40.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.40.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.41.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.41.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.41.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.42.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.42.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.42.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.43.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.43.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.43.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.44.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.44.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.44.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.45.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.45.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.45.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.46.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.46.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.46.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.47.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.47.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.47.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.48.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.48.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.48.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.49.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.49.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.49.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.5.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.5.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.5.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.50.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.50.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.50.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.51.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.51.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.51.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.52.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.52.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.52.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.53.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.53.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.53.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.54.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.54.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.54.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.55.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.55.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.55.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.56.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.56.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.56.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.57.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.57.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.57.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.58.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.58.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.58.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.59.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.59.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.59.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.6.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.6.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.6.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.7.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.7.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.7.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.8.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.8.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.8.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.9.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.9.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.experts.9.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.gate.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.shared_expert.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.shared_expert.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.shared_expert_gate.weight": "model-00005-of-00006.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.0.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.0.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.1.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.1.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.10.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.10.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.10.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.11.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.11.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.11.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.12.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.12.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.12.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.13.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.13.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.13.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.14.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.14.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.14.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.15.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.15.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.15.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.16.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.16.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.16.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.17.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.17.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.17.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.18.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.18.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.18.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.19.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.19.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.19.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.2.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.2.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.20.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.20.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.20.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.21.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.21.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.21.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.22.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.22.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.22.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.23.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.23.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.23.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.24.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.24.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.24.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.25.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.25.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.25.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.26.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.26.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.26.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.27.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.27.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.27.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.28.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.28.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.28.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.29.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.29.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.29.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.3.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.3.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.30.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.30.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.30.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.31.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.31.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.31.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.32.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.32.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.32.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.33.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.33.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.33.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.34.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.34.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.34.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.35.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.35.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.35.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.36.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.36.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.36.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.37.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.37.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.37.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.38.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.38.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.38.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.39.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.39.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.39.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.4.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.4.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.4.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.40.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.40.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.40.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.41.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.41.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.41.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.42.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.42.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.42.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.43.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.43.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.43.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.44.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.44.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.44.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.45.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.45.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.45.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.46.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.46.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.46.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.47.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.47.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.47.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.48.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.48.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.48.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.49.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.49.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.49.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.5.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.5.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.5.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.50.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.50.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.50.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.51.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.51.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.51.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.52.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.52.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.52.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.53.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.53.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.53.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.54.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.54.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.54.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.55.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.55.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.55.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.56.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.56.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.56.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.57.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.57.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.57.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.58.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.58.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.58.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.59.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.59.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.59.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.6.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.6.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.6.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.7.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.7.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.7.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.8.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.8.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.8.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.9.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.9.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.experts.9.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.gate.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.shared_expert.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.shared_expert.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.shared_expert_gate.weight": "model-00001-of-00006.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.20.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.0.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.0.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.1.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.1.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.10.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.10.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.10.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.11.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.11.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.11.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.12.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.12.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.12.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.13.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.13.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.13.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.14.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.14.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.14.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.15.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.15.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.15.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.16.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.16.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.16.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.17.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.17.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.17.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.18.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.18.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.18.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.19.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.19.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.19.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.2.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.2.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.20.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.20.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.20.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.21.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.21.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.21.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.22.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.22.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.22.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.23.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.23.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.23.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.24.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.24.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.24.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.25.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.25.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.25.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.26.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.26.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.26.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.27.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.27.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.27.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.28.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.28.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.28.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.29.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.29.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.29.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.3.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.3.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.30.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.30.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.30.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.31.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.31.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.31.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.32.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.32.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.32.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.33.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.33.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.33.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.34.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.34.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.34.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.35.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.35.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.35.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.36.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.36.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.36.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.37.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.37.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.37.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.38.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.38.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.38.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.39.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.39.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.39.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.4.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.4.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.4.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.40.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.40.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.40.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.41.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.41.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.41.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.42.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.42.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.42.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.43.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.43.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.43.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.44.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.44.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.44.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.45.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.45.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.45.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.46.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.46.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.46.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.47.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.47.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.47.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.48.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.48.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.48.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.49.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.49.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.49.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.5.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.5.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.5.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.50.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.50.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.50.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.51.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.51.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.51.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.52.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.52.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.52.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.53.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.53.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.53.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.54.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.54.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.54.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.55.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.55.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.55.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.56.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.56.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.56.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.57.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.57.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.57.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.58.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.58.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.58.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.59.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.59.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.59.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.6.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.6.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.6.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.7.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.7.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.7.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.8.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.8.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.8.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.9.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.9.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.experts.9.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.gate.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.shared_expert.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.shared_expert.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.shared_expert_gate.weight": "model-00005-of-00006.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.0.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.0.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.1.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.1.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.10.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.10.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.10.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.11.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.11.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.11.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.12.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.12.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.12.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.13.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.13.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.13.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.14.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.14.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.14.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.15.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.15.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.15.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.16.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.16.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.16.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.17.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.17.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.17.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.18.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.18.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.18.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.19.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.19.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.19.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.2.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.2.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.20.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.20.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.20.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.21.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.21.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.21.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.22.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.22.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.22.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.23.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.23.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.23.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.24.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.24.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.24.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.25.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.25.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.25.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.26.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.26.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.26.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.27.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.27.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.27.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.28.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.28.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.28.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.29.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.29.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.29.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.3.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.3.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.30.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.30.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.30.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.31.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.31.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.31.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.32.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.32.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.32.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.33.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.33.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.33.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.34.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.34.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.34.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.35.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.35.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.35.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.36.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.36.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.36.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.37.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.37.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.37.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.38.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.38.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.38.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.39.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.39.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.39.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.4.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.4.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.4.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.40.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.40.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.40.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.41.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.41.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.41.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.42.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.42.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.42.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.43.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.43.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.43.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.44.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.44.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.44.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.45.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.45.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.45.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.46.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.46.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.46.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.47.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.47.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.47.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.48.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.48.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.48.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.49.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.49.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.49.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.5.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.5.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.5.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.50.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.50.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.50.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.51.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.51.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.51.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.52.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.52.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.52.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.53.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.53.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.53.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.54.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.54.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.54.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.55.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.55.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.55.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.56.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.56.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.56.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.57.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.57.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.57.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.58.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.58.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.58.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.59.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.59.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.59.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.experts.6.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.6.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.6.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.7.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.7.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.7.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.8.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.8.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.8.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.9.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.9.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.experts.9.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.gate.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.shared_expert.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.shared_expert.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.22.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.0.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.0.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.1.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.1.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.10.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.10.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.10.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.11.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.11.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.11.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.12.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.12.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.12.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.13.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.13.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.13.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.14.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.14.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.14.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.15.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.15.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.15.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.16.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.16.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.16.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.17.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.17.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.17.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.18.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.18.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.18.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.19.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.19.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.19.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.2.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.2.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.20.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.20.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.20.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.21.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.21.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.21.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.22.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.22.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.22.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.23.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.23.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.23.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.24.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.24.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.24.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.25.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.25.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.25.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.26.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.26.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.26.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.27.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.27.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.27.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.28.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.28.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.28.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.29.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.29.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.29.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.3.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.3.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.30.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.30.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.30.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.31.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.31.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.31.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.32.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.32.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.32.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.33.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.33.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.33.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.34.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.34.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.34.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.35.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.35.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.35.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.36.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.36.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.36.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.37.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.37.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.37.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.38.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.38.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.38.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.39.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.39.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.39.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.4.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.4.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.4.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.40.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.40.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.40.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.41.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.41.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.41.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.42.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.42.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.42.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.43.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.43.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.43.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.44.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.44.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.44.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.45.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.45.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.45.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.46.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.46.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.46.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.47.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.47.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.47.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.48.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.48.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.48.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.49.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.49.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.49.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.5.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.5.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.5.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.50.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.50.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.50.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.51.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.51.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.51.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.52.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.52.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.52.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.53.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.53.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.53.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.54.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.54.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.54.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.55.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.55.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.55.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.56.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.56.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.56.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.57.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.57.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.57.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.58.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.58.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.58.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.59.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.59.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.59.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.6.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.6.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.6.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.7.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.7.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.7.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.8.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.8.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.8.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.9.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.9.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.experts.9.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.gate.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.shared_expert.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.shared_expert.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.0.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.0.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.1.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.1.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.10.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.10.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.10.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.11.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.11.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.11.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.12.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.12.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.12.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.13.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.13.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.13.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.14.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.14.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.14.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.15.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.15.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.15.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.16.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.16.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.16.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.17.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.17.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.17.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.18.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.18.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.18.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.19.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.19.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.19.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.2.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.2.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.20.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.20.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.20.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.21.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.21.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.21.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.22.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.22.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.22.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.23.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.23.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.23.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.24.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.24.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.24.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.25.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.25.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.25.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.26.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.26.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.26.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.27.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.27.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.27.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.28.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.28.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.28.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.29.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.29.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.29.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.3.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.3.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.30.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.30.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.30.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.31.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.31.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.31.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.32.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.32.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.32.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.33.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.33.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.33.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.34.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.34.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.34.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.35.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.35.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.35.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.36.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.36.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.36.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.37.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.37.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.37.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.38.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.38.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.38.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.39.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.39.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.39.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.4.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.4.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.40.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.40.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.40.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.41.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.41.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.41.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.42.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.42.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.42.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.43.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.43.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.43.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.44.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.44.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.44.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.45.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.45.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.45.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.46.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.46.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.46.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.47.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.47.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.47.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.48.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.48.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.48.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.49.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.49.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.49.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.5.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.5.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.5.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.50.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.50.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.50.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.51.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.51.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.51.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.52.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.52.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.52.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.53.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.53.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.53.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.54.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.54.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.54.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.55.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.55.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.55.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.56.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.56.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.56.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.57.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.57.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.57.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.58.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.58.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.58.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.59.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.59.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.59.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.6.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.6.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.6.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.7.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.7.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.7.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.8.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.8.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.8.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.9.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.9.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.experts.9.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.gate.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.shared_expert.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.shared_expert.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.shared_expert_gate.weight": "model-00006-of-00006.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.experts.0.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.0.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.1.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.1.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.10.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.10.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.11.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.11.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.12.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.12.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.13.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.13.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.14.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.14.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.15.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.15.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.16.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.16.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.17.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.17.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.18.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.18.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.19.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.19.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.2.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.2.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.20.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.20.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.21.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.21.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.22.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.22.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.23.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.23.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.24.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.24.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.25.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.25.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.26.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.26.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.27.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.27.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.28.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.28.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.29.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.29.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.3.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.3.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.30.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.30.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.31.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.31.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.32.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.32.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.33.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.33.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.34.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.34.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.35.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.35.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.36.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.36.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.37.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.37.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.38.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.38.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.39.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.39.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.4.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.4.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.40.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.40.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.41.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.41.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.42.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.42.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.43.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.43.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.44.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.44.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.45.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.45.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.46.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.46.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.47.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.47.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.48.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.48.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.49.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.49.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.5.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.5.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.50.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.50.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.51.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.51.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.52.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.52.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.53.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.experts.53.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.experts.54.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.experts.54.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.experts.55.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.experts.55.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.experts.56.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.experts.56.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.experts.57.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.experts.57.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.experts.58.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.experts.58.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.experts.59.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.experts.59.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.experts.6.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.6.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.7.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.7.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.8.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.8.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.9.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.experts.9.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.gate.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.shared_expert.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.shared_expert.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.shared_expert_gate.weight": "model-00002-of-00006.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.0.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.0.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.1.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.1.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.10.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.10.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.11.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.11.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.12.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.12.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.13.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.13.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.14.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.14.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.15.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.15.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.16.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.16.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.17.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.17.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.18.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.18.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.19.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.19.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.2.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.2.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.20.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.20.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.21.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.21.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.22.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.22.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.23.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.23.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.24.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.24.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.25.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.25.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.26.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.26.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.27.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.27.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.28.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.28.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.29.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.29.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.3.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.3.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.30.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.30.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.31.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.31.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.32.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.32.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.33.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.33.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.34.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.34.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.35.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.35.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.36.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.36.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.37.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.37.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.38.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.38.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.39.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.39.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.4.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.4.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.40.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.40.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.41.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.41.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.42.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.42.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.43.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.43.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.44.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.44.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.45.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.45.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.46.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.46.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.47.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.47.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.48.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.48.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.49.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.49.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.5.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.5.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.50.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.50.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.51.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.51.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.52.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.52.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.53.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.53.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.54.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.54.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.55.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.55.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.56.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.56.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.57.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.57.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.58.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.58.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.59.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.59.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.6.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.6.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.7.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.7.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.8.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.8.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.9.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.experts.9.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.gate.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.shared_expert.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.shared_expert.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.shared_expert_gate.weight": "model-00002-of-00006.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.0.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.0.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.1.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.1.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.10.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.10.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.10.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.11.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.11.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.11.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.12.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.12.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.12.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.13.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.13.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.13.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.14.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.14.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.14.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.15.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.15.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.15.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.16.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.16.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.16.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.17.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.17.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.17.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.18.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.18.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.18.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.19.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.19.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.19.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.2.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.2.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.20.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.20.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.20.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.21.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.21.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.21.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.22.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.22.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.22.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.23.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.23.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.23.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.24.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.24.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.24.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.25.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.25.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.25.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.26.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.26.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.26.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.27.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.27.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.27.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.28.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.28.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.28.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.29.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.29.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.29.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.3.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.3.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.30.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.30.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.30.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.31.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.31.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.31.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.32.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.32.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.32.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.33.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.33.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.33.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.34.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.34.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.34.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.35.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.35.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.35.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.36.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.36.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.36.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.37.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.37.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.37.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.38.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.38.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.38.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.39.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.39.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.39.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.4.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.4.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.40.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.40.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.40.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.41.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.41.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.41.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.42.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.42.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.42.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.43.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.43.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.43.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.44.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.44.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.44.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.45.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.45.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.45.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.46.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.46.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.46.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.47.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.47.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.47.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.48.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.48.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.48.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.49.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.49.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.49.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.5.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.5.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.50.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.50.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.50.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.51.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.51.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.51.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.52.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.52.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.52.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.53.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.53.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.53.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.54.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.54.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.54.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.55.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.55.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.55.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.56.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.56.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.56.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.57.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.57.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.57.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.58.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.58.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.58.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.59.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.59.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.59.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.6.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.6.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.7.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.7.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.8.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.8.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.8.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.9.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.9.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.experts.9.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.gate.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.shared_expert.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.shared_expert.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.shared_expert_gate.weight": "model-00002-of-00006.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.0.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.0.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.1.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.1.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.10.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.10.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.10.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.11.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.11.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.11.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.12.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.12.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.12.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.13.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.13.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.13.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.14.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.14.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.14.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.15.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.15.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.15.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.16.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.16.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.16.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.17.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.17.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.17.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.18.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.18.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.18.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.19.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.19.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.19.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.2.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.2.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.20.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.20.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.20.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.21.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.21.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.21.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.22.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.22.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.22.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.23.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.23.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.23.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.24.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.24.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.24.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.25.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.25.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.25.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.26.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.26.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.26.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.27.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.27.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.27.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.28.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.28.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.28.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.29.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.29.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.29.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.3.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.3.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.30.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.30.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.30.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.31.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.31.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.31.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.32.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.32.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.32.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.33.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.33.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.33.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.34.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.34.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.34.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.35.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.35.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.35.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.36.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.36.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.36.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.37.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.37.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.37.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.38.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.38.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.38.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.39.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.39.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.39.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.4.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.4.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.40.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.40.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.40.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.41.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.41.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.41.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.42.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.42.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.42.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.43.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.43.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.43.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.44.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.44.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.44.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.45.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.45.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.45.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.46.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.46.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.46.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.47.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.47.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.47.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.48.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.48.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.48.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.49.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.49.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.49.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.5.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.5.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.5.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.50.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.50.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.50.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.51.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.51.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.51.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.52.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.52.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.52.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.53.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.53.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.53.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.54.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.54.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.54.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.55.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.55.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.55.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.56.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.56.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.56.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.57.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.57.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.57.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.58.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.58.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.58.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.59.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.59.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.59.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.6.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.6.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.6.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.7.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.7.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.7.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.8.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.8.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.8.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.9.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.9.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.experts.9.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.gate.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.shared_expert.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.shared_expert.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.shared_expert_gate.weight": "model-00002-of-00006.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.0.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.0.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.1.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.1.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.10.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.10.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.10.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.11.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.11.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.11.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.12.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.12.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.12.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.13.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.13.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.13.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.14.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.14.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.14.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.15.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.15.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.15.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.16.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.16.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.16.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.17.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.17.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.17.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.18.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.18.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.18.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.19.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.19.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.19.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.2.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.2.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.20.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.20.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.20.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.21.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.21.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.21.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.22.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.22.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.22.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.23.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.23.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.23.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.24.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.24.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.24.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.25.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.25.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.25.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.26.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.26.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.26.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.27.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.27.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.27.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.28.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.28.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.28.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.29.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.29.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.29.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.3.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.3.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.30.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.30.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.30.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.31.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.31.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.31.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.32.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.32.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.32.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.33.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.33.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.33.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.34.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.34.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.34.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.35.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.35.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.35.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.36.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.36.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.36.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.37.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.37.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.37.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.38.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.38.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.38.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.39.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.39.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.39.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.4.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.4.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.4.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.40.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.40.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.40.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.41.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.41.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.41.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.42.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.42.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.42.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.43.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.43.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.43.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.44.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.44.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.44.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.45.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.45.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.45.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.46.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.46.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.46.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.47.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.47.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.47.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.48.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.48.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.48.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.49.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.49.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.49.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.5.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.5.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.5.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.50.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.50.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.50.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.51.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.51.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.51.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.52.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.52.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.52.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.53.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.53.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.53.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.54.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.54.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.54.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.55.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.55.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.55.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.56.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.56.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.56.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.57.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.57.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.57.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.58.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.58.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.58.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.59.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.59.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.59.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.6.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.6.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.6.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.7.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.7.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.7.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.8.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.8.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.8.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.9.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.9.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.experts.9.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.gate.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.shared_expert.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.shared_expert.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.shared_expert_gate.weight": "model-00002-of-00006.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.0.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.0.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.1.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.1.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.10.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.10.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.10.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.11.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.11.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.11.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.12.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.12.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.12.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.13.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.13.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.13.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.14.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.14.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.14.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.15.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.15.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.15.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.16.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.16.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.16.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.17.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.17.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.17.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.18.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.18.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.18.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.19.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.19.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.19.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.2.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.2.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.20.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.20.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.20.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.21.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.21.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.21.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.22.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.22.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.22.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.23.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.23.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.23.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.24.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.24.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.24.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.25.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.25.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.25.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.26.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.26.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.26.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.27.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.27.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.27.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.28.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.28.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.28.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.29.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.29.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.29.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.3.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.3.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.30.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.30.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.30.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.31.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.31.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.31.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.32.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.32.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.32.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.33.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.33.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.33.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.34.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.34.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.34.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.35.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.35.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.35.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.36.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.36.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.36.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.37.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.37.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.37.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.38.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.38.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.38.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.39.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.39.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.39.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.4.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.4.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.40.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.40.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.40.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.41.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.41.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.41.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.42.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.42.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.42.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.43.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.43.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.43.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.44.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.44.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.44.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.45.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.45.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.45.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.46.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.46.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.46.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.47.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.47.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.47.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.48.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.48.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.48.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.49.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.49.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.49.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.5.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.5.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.5.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.50.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.50.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.50.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.51.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.51.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.51.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.52.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.52.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.52.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.53.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.53.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.53.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.54.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.54.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.54.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.55.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.55.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.55.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.56.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.56.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.56.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.57.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.57.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.57.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.58.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.58.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.58.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.59.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.59.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.59.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.experts.6.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.6.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.6.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.7.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.7.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.7.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.8.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.8.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.8.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.9.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.9.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.experts.9.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.gate.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.shared_expert.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.shared_expert.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.8.mlp.shared_expert_gate.weight": "model-00003-of-00006.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.0.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.0.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.1.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.1.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.10.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.10.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.10.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.11.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.11.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.11.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.12.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.12.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.12.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.13.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.13.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.13.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.14.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.14.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.14.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.15.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.15.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.15.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.16.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.16.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.16.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.17.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.17.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.17.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.18.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.18.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.18.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.19.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.19.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.19.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.2.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.2.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.20.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.20.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.20.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.21.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.21.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.21.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.22.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.22.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.22.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.23.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.23.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.23.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.24.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.24.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.24.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.25.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.25.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.25.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.26.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.26.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.26.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.27.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.27.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.27.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.28.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.28.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.28.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.29.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.29.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.29.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.3.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.3.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.30.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.30.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.30.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.31.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.31.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.31.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.32.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.32.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.32.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.33.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.33.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.33.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.34.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.34.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.34.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.35.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.35.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.35.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.36.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.36.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.36.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.37.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.37.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.37.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.38.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.38.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.38.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.39.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.39.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.39.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.4.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.4.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.40.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.40.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.40.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.41.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.41.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.41.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.42.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.42.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.42.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.43.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.43.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.43.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.44.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.44.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.44.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.45.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.45.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.45.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.46.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.46.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.46.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.47.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.47.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.47.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.48.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.48.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.48.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.49.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.49.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.49.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.5.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.5.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.5.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.50.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.50.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.50.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.51.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.51.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.51.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.52.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.52.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.52.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.53.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.53.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.53.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.54.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.54.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.54.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.55.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.55.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.55.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.56.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.56.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.56.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.57.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.57.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.57.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.58.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.58.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.58.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.59.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.59.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.59.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.6.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.6.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.6.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.7.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.7.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.7.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.8.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.8.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.8.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.9.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.9.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.experts.9.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.gate.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.shared_expert.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.shared_expert.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.mlp.shared_expert_gate.weight": "model-00003-of-00006.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.norm.weight": "model-00006-of-00006.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..63fbc67 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,20 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>" + ], + "eos_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..611910f --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7c9b2dba4a296b1aa76c16a34b8225c0c118978400d4bb66bff0902d702f5b8 +size 7028015 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..d881249 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,43 @@ +{ + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>" + ], + "bos_token": null, + "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<|endoftext|>", + "errors": "replace", + "model_max_length": 32768, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833