初始化项目，由ModelHub XC社区提供模型

Model: llm-jp/optimal-sparsity-math-d2048-E8-k8-3.9B-A3.9B
Source: Original Platform

.gitattributes

@@ -0,0 +1,51 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+ 
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,31 @@
+---
+pipeline_tag: text-generation
+library_name: transformers
+license: apache-2.0
+tags:
+  - mixtral
+  - moe
+  - reasoning
+---
+
+# Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks
+
+This repository contains model checkpoints from the paper [Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks](https://huggingface.co/papers/2508.18672).
+
+For more details, including code and evaluation procedures, please refer to the official GitHub repository: [https://github.com/rioyokotalab/optimal-sparsity](https://github.com/rioyokotalab/optimal-sparsity)
+
+## How to cite
+
+If you find our work helpful, please feel free to cite the paper.
+
+```bibtex
+@inproceedings{
+    nakamura2026optimal,
+    title={Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks},
+    author={Taishi Nakamura and Satoki Ishikawa and Masaki Kawamura and Takumi Okamoto and Daisuke Nohara and Jun Suzuki and Rio Yokota},
+    booktitle={The Fourteenth International Conference on Learning Representations},
+    year={2026},
+    url={https://openreview.net/forum?id=XFw2EPRUUR}
+}
+```
+

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "mixtral",
+  "num_attention_heads": 16,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 16,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000,
+  "router_aux_loss_coef": 0.01,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0",
+  "use_cache": true,
+  "vocab_size": 99584
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be4bdf9ef6ed7735695faa24d7b2629a98c9d7a49da42d6d1df96b5082f5a7e2
+size 4988775992

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c99ba10bd8da31f12e50e9aab76520c4d1376d4ef2bb67c6b9db682e84f26df
+size 2807060840

model.safetensors.index.json

@@ -0,0 +1,506 @@
+{
+  "metadata": {
+    "total_size": 7795773440
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "lm_head.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,10 @@
+{
+    "bos_token": "<s>",
+    "cls_token": "<CLS|LLM-jp>",
+    "eod_token": "</s>",
+    "eos_token": "</s>",
+    "mask_token": "<MASK|LLM-jp>",
+    "pad_token": "<PAD|LLM-jp>",
+    "sep_token": "<SEP|LLM-jp>",
+    "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:955dc1fa623fab38cc92a3f4ee172423ae6d73201c4207569bfdf5626bc733f0
+size 6416433

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "unk_token": "<unk>",
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<PAD|LLM-jp>",
+  "cls_token": "<CLS|LLM-jp>",
+  "sep_token": "<SEP|LLM-jp>",
+  "eod_token": "</s>",
+  "mask_token": "<MASK|LLM-jp>",
+  "extra_ids": 0,
+  "sp_model_kwargs": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "clean_up_tokenization_spaces": false,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}