初始化项目，由ModelHub XC社区提供模型

Model: llm-jp/optimal-sparsity-code-d2048-E64-k4-26.4B-A2.3B
Source: Original Platform

.gitattributes

@@ -0,0 +1,60 @@
+*.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-00004-of-00011.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model-00005-of-00011.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00009-of-00011.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00008-of-00011.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00007-of-00011.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00011.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00006-of-00011.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00010-of-00011.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00011-of-00011.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00011.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00011.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": 4,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 16,
+  "num_local_experts": 64,
+  "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-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd862d19352933eb6bf5b4fd37d54a94017000b9a6a5512faf7f73702d4c3100
+size 4992445944

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d40b386bb4c1bc6bae8a3afd1eb14117cd8a51e2767d38a4a334614379e09d4b
+size 4999649272

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a59ddbddd8bb0be28dd454e7f3af646291df9762d4e2f8008a322bca04fe2255
+size 4999649400

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:917ab5f1ca1172883fbdd970b7b399f7ce5b8fb4347191f65e9868a10d05baf9
+size 4999649440

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dabaf4cb4a5724d63f7cbd1a88018c8dab05850007f907623d4e72d7d95eb6e3
+size 4999649368

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6cddfd752de0980c3f008a9a99c6591c5e731453845d30c7ab13a2ce1661b8c
+size 4999649416

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f574c05e36062f3f1df48443982979cfe5462c9a6343a1cc4ebf6309bb3eb89d
+size 4999649456

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67be2f4b51fd539fb8b589f0e5fc1dc75e2e76c03ff6e9fb5dd62d9f0fa82a89
+size 4999649456

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07dbb7bb96696bf2d7b67b061ff0dfb3e3a6b281bc8609524f7b5367d0087786
+size 4999649392

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9af4b6bfbc8ca26579c1ea60703f2b5f3d129b46d495393d1bf15a068e719f5
+size 4999649376

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93d81d7e9f8affb1193b994a02b5cbfd5a42c4cbdc35d4b8ea32be7befefdfd3
+size 2907725152

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"
+}