commit 9094cee8aac963a080991827b28aa53c6ddce2f3 Author: ModelHub XC Date: Wed Aug 12 03:09:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: corag/CoRAG-Llama3.1-8B-MultihopQA Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..386dec2 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,38 @@ +*.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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text +tokenizer_config.json filter=lfs diff=lfs merge=lfs -text +model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1f9ddb7 --- /dev/null +++ b/README.md @@ -0,0 +1,40 @@ +--- +license: apache-2.0 +--- + +# CoRAG-Llama3.1-8B-MultihopQA + +This is the CoRAG-8B model fine-tuned on [MultihopQA data](https://huggingface.co/datasets/corag/multihopqa) in the paper [Chain-of-Retrieval Augmented Generation](https://arxiv.org/abs/2501.14342). + +## Model Evaluation + +| **Model** | **2WikiQA EM** | **2WikiQA F1** | **HotpotQA EM** | **HotpotQA F1** | **Bamboogle EM** | **Bamboogle F1** | **MuSiQue EM** | **MuSiQue F1** | +|----------------------------------------|----------------|----------------|------------------|------------------|------------------|------------------|----------------|----------------| +| **3-shot Llama-3.1-8B-Inst.** | 30.7 | 39.9 | 34.1 | 46.6 | 28.0 | 37.3 | 7.7 | 15.4 | +| **3-shot GPT-4o** | 49.0 | 56.2 | 45.8 | 59.4 | 53.6 | 63.8 | 15.7 | 25.8 | +| **Fine-tuned Llama-8B w/ E5large** | 55.1 | 60.7 | 50.3 | 63.5 | 40.8 | 53.7 | 17.4 | 28.1 | +| **CoRAG-8B (Ours)** | | | | | | | | | +| > L=1, greedy | 56.5 | 62.3 | 50.1 | 63.2 | 37.6 | 51.4 | 18.6 | 29.3 | +| > L=6, greedy | 70.6 | 75.5 | 54.4 | 67.5 | 48.0 | 63.5 | 27.7 | 38.5 | +| > L=6, best-of-4 | 71.7 | 76.5 | 55.3 | 68.5 | 51.2 | 63.1 | 28.1 | 39.7 | +| > L=6, tree search | 71.7 | 76.4 | 55.8 | 69.0 | 48.8 | 64.4 | 29.0 | 40.3 | +| > L=10, best-of-8 | **72.5** | **77.3** | **56.3** | **69.8** | **54.4** | **68.3** | **30.9** | **42.4** | + +Please refer to [https://github.com/microsoft/LMOps/tree/main/corag](https://github.com/microsoft/LMOps/tree/main/corag) for evaluation instructions. + +Model predictions are available as the `predictions` field at https://huggingface.co/datasets/corag/multihopqa + +## Disclaimer + +This model has been specifically trained for the task of MultihopQA. It may not perform well on other tasks. + +## References + +``` +@article{wang2025chain, + title={Chain-of-Retrieval Augmented Generation}, + author={Wang, Liang and Chen, Haonan and Yang, Nan and Huang, Xiaolong and Dou, Zhicheng and Wei, Furu}, + journal={arXiv preprint arXiv:2501.14342}, + year={2025} +} +``` diff --git a/config.json b/config.json new file mode 100644 index 0000000..1c6d515 --- /dev/null +++ b/config.json @@ -0,0 +1,41 @@ +{ + "_name_or_path": "corag-8b/", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 128001, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.49.0", + "use_cache": false, + "vocab_size": 128256 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..a01c84e --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.49.0" +} diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..27fcad8 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d4931987d2ec28687b8f2aa144eef7a85807f96fb8678c34ea5066d7877d6aa +size 4976698672 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..3c42593 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f47d7d9b5b9474020d5fa65ed8898661f7bc532e89cea00e0dd8e425e1207337 +size 4999802720 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..caf7dc6 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:240f79a2c7f09b68d46d1c5e93163a3dc38e86a69956f00ebc7e944a7e4d6146 +size 4915916176 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..f65825a --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18ea1535ca203550613219cd1960f57a8ef29eff27593282c14a15f217fa27fb +size 1168138808 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..a054aad --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:146776fce3f6db1103aa6f249e65ee5544c5923ce6f971b092eee79aa6e5d37b +size 23950 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..344c826 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..1c1d8d5 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..08335e8 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf9caa6e3956c24f5787bff455fccb25532afa5091d6b8cbee01a5b7235a1362 +size 55406