commit fae8bd2d396bc95dae038323a7bd11233f024d94 Author: ModelHub XC Date: Sat Jun 13 13:52:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: maywell/Synatra-Mixtral-8x7B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt 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 +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz 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 +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl 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 +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* 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 +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..3c4b135 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +license: apache-2.0 +language: +- ko +- en +tags: +- moe +--- + +# **Synatra-Mixtral-8x7B** +Synatra-Mixtral-8x7B + + +**Synatra-Mixtral-8x7B** is a fine-tuned version of the Mixtral-8x7B-Instruct-v0.1 model using **Korean** datasets. + +This model features overwhelmingly superior comprehension and inference capabilities and is licensed under apache-2.0. + +# **Join Our Discord** + +[Server Link](https://discord.gg/MrBt3PXdXc) + +# **License** + +**OPEN**, Apache-2.0. + +# **Model Details** + +**Base Model** +[mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) + +**Trained On** +A100 80GB * 6 + +**Instruction format** + +It follows **Alpaca** format. +``` +Below is an instruction that describes a task. Write a response that appropriately completes the request. + +### Instruction: +{input} + +### Response: +{output} +``` + +# **Model Benchmark** +TBD + +# **Implementation Code** + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +device = "cuda" # the device to load the model onto + +model = AutoModelForCausalLM.from_pretrained("maywell/Synatra-Mixtral-8x7B") +tokenizer = AutoTokenizer.from_pretrained("maywell/Synatra-Mixtral-8x7B") + +messages = [ + {"role": "user", "content": "아인슈타인의 상대성이론에 대해서 자세히 설명해줘."}, +] + +encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt") + +model_inputs = encodeds.to(device) +model.to(device) + +generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True) +decoded = tokenizer.batch_decode(generated_ids) +print(decoded[0]) +``` + +# **Author's Message** + +This model's training got sponsered by no one but support from people around Earth. + +[Support Me](https://www.buymeacoffee.com/mwell) + +Contact Me on Discord - **is.maywell** + +Follow me on twitter: https://twitter.com/stablefluffy \ No newline at end of file diff --git a/Synatra-Mixtral.png b/Synatra-Mixtral.png new file mode 100644 index 0000000..d70ddff Binary files /dev/null and b/Synatra-Mixtral.png differ diff --git a/config.json b/config.json new file mode 100644 index 0000000..afe3a64 --- /dev/null +++ b/config.json @@ -0,0 +1,30 @@ +{ + "_name_or_path": "maywell/Synatra-Mixtral-8x7B", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mixtral", + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": true, + "rms_norm_eps": 1e-05, + "rope_theta": 1000000.0, + "router_aux_loss_coef": 0.02, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.37.0.dev0", + "use_cache": false, + "vocab_size": 32000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..1692386 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.37.0.dev0" +} diff --git a/pytorch_model-00001-of-00019.bin b/pytorch_model-00001-of-00019.bin new file mode 100644 index 0000000..7082900 --- /dev/null +++ b/pytorch_model-00001-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abbb9434f6f993dcb3353c8a459e44a9c6580ec98d214eada5a1ffc3057274f1 +size 4892821505 diff --git a/pytorch_model-00002-of-00019.bin b/pytorch_model-00002-of-00019.bin new file mode 100644 index 0000000..be9f205 --- /dev/null +++ b/pytorch_model-00002-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:196d64071d1d59f729381f96cdbe3f21eb5ac72a30e2e3cd521a3116c4aa3bee +size 4983016829 diff --git a/pytorch_model-00003-of-00019.bin b/pytorch_model-00003-of-00019.bin new file mode 100644 index 0000000..7b93fe8 --- /dev/null +++ b/pytorch_model-00003-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ed1a3a29ec23bb08012bfda8c8a194ed4f4606290976595e78e1e2e5ff06f61 +size 4983016913 diff --git a/pytorch_model-00004-of-00019.bin b/pytorch_model-00004-of-00019.bin new file mode 100644 index 0000000..c7b102d --- /dev/null +++ b/pytorch_model-00004-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31441768234a6d900dc3dce897d0ad2c6601a9205123f3a55b28a97b4209e77e +size 4899046399 diff --git a/pytorch_model-00005-of-00019.bin b/pytorch_model-00005-of-00019.bin new file mode 100644 index 0000000..366c7ce --- /dev/null +++ b/pytorch_model-00005-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:891795cfb3f8a334d08f760bfde3d9ae4695daa3bc1c94e32b0234f90b0df560 +size 4983016865 diff --git a/pytorch_model-00006-of-00019.bin b/pytorch_model-00006-of-00019.bin new file mode 100644 index 0000000..8818bc8 --- /dev/null +++ b/pytorch_model-00006-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df5adf9034c66f6229163fed006fb9731a796eb8cb5748257fa6dfb2151f9388 +size 4983016893 diff --git a/pytorch_model-00007-of-00019.bin b/pytorch_model-00007-of-00019.bin new file mode 100644 index 0000000..49b5ed0 --- /dev/null +++ b/pytorch_model-00007-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:760cc2135776f4e72d6e2f3283168158f734a920778192d6d5696eeaf322f641 +size 4899046463 diff --git a/pytorch_model-00008-of-00019.bin b/pytorch_model-00008-of-00019.bin new file mode 100644 index 0000000..881099f --- /dev/null +++ b/pytorch_model-00008-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7540562870e40a4b3f5a8acf1a511adf2fecc4fb44732084cb1a2babdc7b084b +size 4983016953 diff --git a/pytorch_model-00009-of-00019.bin b/pytorch_model-00009-of-00019.bin new file mode 100644 index 0000000..28150a4 --- /dev/null +++ b/pytorch_model-00009-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb5040aded82219ffa9e78f0f25ddd1047166d14417cc17ba891b7a2513cc530 +size 4983016893 diff --git a/pytorch_model-00010-of-00019.bin b/pytorch_model-00010-of-00019.bin new file mode 100644 index 0000000..2f150b0 --- /dev/null +++ b/pytorch_model-00010-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8582bff83ef1639bf8fe82bf2f0b91d1613e98a95c7411eabe949e0b033ed251 +size 4899046463 diff --git a/pytorch_model-00011-of-00019.bin b/pytorch_model-00011-of-00019.bin new file mode 100644 index 0000000..e915735 --- /dev/null +++ b/pytorch_model-00011-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85e67b8b57c5b309ced69a1d438abf4b4f500b648925aaaf3bd2b37897b80323 +size 4983016917 diff --git a/pytorch_model-00012-of-00019.bin b/pytorch_model-00012-of-00019.bin new file mode 100644 index 0000000..87caeee --- /dev/null +++ b/pytorch_model-00012-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b82dc2e51e6519005d67e1fd467e8b40ae26a31fa0320b56fc5c126f3fca408 +size 4983016917 diff --git a/pytorch_model-00013-of-00019.bin b/pytorch_model-00013-of-00019.bin new file mode 100644 index 0000000..0628154 --- /dev/null +++ b/pytorch_model-00013-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82604cb32a6a31e202078b1912bc882f368b87b0c50b3734b4fdd88078b77f19 +size 4983016893 diff --git a/pytorch_model-00014-of-00019.bin b/pytorch_model-00014-of-00019.bin new file mode 100644 index 0000000..9c4909e --- /dev/null +++ b/pytorch_model-00014-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b65079309a0163f64d1761b597e920ff8cc886a9b31b98ade1450099249c1f4 +size 4899046463 diff --git a/pytorch_model-00015-of-00019.bin b/pytorch_model-00015-of-00019.bin new file mode 100644 index 0000000..455f082 --- /dev/null +++ b/pytorch_model-00015-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45e6e9d8a1377d98e1fd472d0bdb3e4067307df5acde32dccadb32d674464b0a +size 4983016953 diff --git a/pytorch_model-00016-of-00019.bin b/pytorch_model-00016-of-00019.bin new file mode 100644 index 0000000..f79bcff --- /dev/null +++ b/pytorch_model-00016-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30a0c45e9cc6f0f34b75927c4cce382b8a6c31e266e282f2c43670b83f0ddd6a +size 4983016893 diff --git a/pytorch_model-00017-of-00019.bin b/pytorch_model-00017-of-00019.bin new file mode 100644 index 0000000..64d9e04 --- /dev/null +++ b/pytorch_model-00017-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71e52c26fe1158c18ae7db159f277faa2560b7f2f5529767112bbdf00c62b0c3 +size 4899046463 diff --git a/pytorch_model-00018-of-00019.bin b/pytorch_model-00018-of-00019.bin new file mode 100644 index 0000000..46479fd --- /dev/null +++ b/pytorch_model-00018-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63309e951834fb5ffbda2ffd576336d4311dc4287f2f915189e147d5c678b50f +size 4983016929 diff --git a/pytorch_model-00019-of-00019.bin b/pytorch_model-00019-of-00019.bin new file mode 100644 index 0000000..aecab54 --- /dev/null +++ b/pytorch_model-00019-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89ae1fc23bbbb478d3c04f4fcaff63b4f60e65a3792c8b854080e9aba898afa6 +size 4221689255 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..c105000 --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,1002 @@ +{ + "metadata": { + "total_size": 93405585408 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00019-of-00019.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.gate.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.11.block_sparse_moe.gate.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.gate.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.block_sparse_moe.gate.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.gate.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.gate.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.16.block_sparse_moe.gate.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.gate.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.18.block_sparse_moe.gate.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.gate.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.gate.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.gate.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.gate.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.23.block_sparse_moe.gate.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.gate.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.block_sparse_moe.gate.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.gate.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.gate.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.28.block_sparse_moe.gate.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.gate.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.30.block_sparse_moe.gate.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.gate.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.6.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.gate.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.gate.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.gate.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.norm.weight": "pytorch_model-00019-of-00019.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..72ecfee --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..8b443ef --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..c3b3e00 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,45 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "chat_template": "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n{% for message in messages %}{% if message['role'] == 'user' %}### Instruction:\n{{ message['content']|trim -}}{% if not loop.last %}{% endif %}\n{% elif message['role'] == 'assistant' %}### Response:\n{{ message['content']|trim -}}{% if not loop.last %}{% endif %}\n{% elif message['role'] == 'system' %}{{ message['content']|trim -}}{% if not loop.last %}{% endif %}\n{% endif %}\n{% endfor %}\n{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}\n### Response:\n{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "trust_remote_code": true, + "unk_token": "", + "use_default_system_prompt": false, + "use_fast": true +}