commit 44a256cfa167e2d391d85ee504a93bab01f5bb84 Author: ModelHub XC Date: Mon Apr 13 03:19:54 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: llm-jp/optimal-sparsity-math-d512-E64-k16-1.7B-A520M Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..16332c1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 + +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..2b002e9 --- /dev/null +++ b/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} +} +``` + diff --git a/config.json b/config.json new file mode 100644 index 0000000..1dd0f5a --- /dev/null +++ b/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": 512, + "initializer_range": 0.02, + "intermediate_size": 1024, + "max_position_embeddings": 4096, + "mlp_bias": false, + "model_type": "mixtral", + "num_attention_heads": 4, + "num_experts_per_tok": 16, + "num_hidden_layers": 16, + "num_key_value_heads": 4, + "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 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..f4c1ec5 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cae224ce99c30d33e378b8e843e0b8686d7c4650f6e3ecb0d911a1c09e2a4f19 +size 3460222080 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..8644c8f --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,10 @@ +{ + "bos_token": "", + "cls_token": "", + "eod_token": "", + "eos_token": "", + "mask_token": "", + "pad_token": "", + "sep_token": "", + "unk_token": "" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..fc80107 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:955dc1fa623fab38cc92a3f4ee172423ae6d73201c4207569bfdf5626bc733f0 +size 6416433 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..09aa857 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,18 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "unk_token": "", + "bos_token": "", + "eos_token": "", + "pad_token": "", + "cls_token": "", + "sep_token": "", + "eod_token": "", + "mask_token": "", + "extra_ids": 0, + "sp_model_kwargs": {}, + "model_max_length": 1000000000000000019884624838656, + "clean_up_tokenization_spaces": false, + "special_tokens_map_file": null, + "tokenizer_class": "PreTrainedTokenizerFast" +}