commit 6d6a9a880e529f71cd74736d0bf0064a282e53ec Author: ModelHub XC Date: Wed Jun 24 15:21:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: QuantFactory/MMed-Llama-3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5a744dc --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +MMed-Llama-3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MMed-Llama-3-8B.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +MMed-Llama-3-8B.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +MMed-Llama-3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MMed-Llama-3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MMed-Llama-3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MMed-Llama-3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MMed-Llama-3-8B.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +MMed-Llama-3-8B.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +MMed-Llama-3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MMed-Llama-3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MMed-Llama-3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MMed-Llama-3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MMed-Llama-3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MMed-Llama-3-8B.Q2_K.gguf b/MMed-Llama-3-8B.Q2_K.gguf new file mode 100644 index 0000000..1311862 --- /dev/null +++ b/MMed-Llama-3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f64d7476fcb45d9aa1955f947f3bf9c3cf1818f47c4c75bb4e3cc08c27a5c00 +size 3179131616 diff --git a/MMed-Llama-3-8B.Q3_K_L.gguf b/MMed-Llama-3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..8c6f769 --- /dev/null +++ b/MMed-Llama-3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdf6b90069cbe92758cbcc8f1beda44e94f8a1d01bb26a3fa031822a0ba18ccd +size 4321956576 diff --git a/MMed-Llama-3-8B.Q3_K_M.gguf b/MMed-Llama-3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..04e508b --- /dev/null +++ b/MMed-Llama-3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a724099181a5b20fed7e359bc07f50e5c7b90900dc2d7f665ef20e85d5e83d2f +size 4018918112 diff --git a/MMed-Llama-3-8B.Q3_K_S.gguf b/MMed-Llama-3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..98461d2 --- /dev/null +++ b/MMed-Llama-3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8bec73c54c13eab19b33bb9a28125d72ca1f3833643beb26c7f8e54b4bc3e9b +size 3664499424 diff --git a/MMed-Llama-3-8B.Q4_0.gguf b/MMed-Llama-3-8B.Q4_0.gguf new file mode 100644 index 0000000..3bcf7fd --- /dev/null +++ b/MMed-Llama-3-8B.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78af66429d8df93ea3335358f4dc22ed80dab863c8feb25856f10cf1f5b6500b +size 4661211872 diff --git a/MMed-Llama-3-8B.Q4_1.gguf b/MMed-Llama-3-8B.Q4_1.gguf new file mode 100644 index 0000000..e60cfb6 --- /dev/null +++ b/MMed-Llama-3-8B.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e108c73af977f482b2bb51a6fa900c9e8c1b09ffbea9f440946b1ffc821d266e +size 5130253024 diff --git a/MMed-Llama-3-8B.Q4_K_M.gguf b/MMed-Llama-3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..bd5ea7e --- /dev/null +++ b/MMed-Llama-3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aafd30eb737ca5a3b1443e1a6474dc56b93f1c8ec364fb42a921049611ff53fc +size 4920734432 diff --git a/MMed-Llama-3-8B.Q4_K_S.gguf b/MMed-Llama-3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..7a0ef37 --- /dev/null +++ b/MMed-Llama-3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2807fa26405097e44f2ccb68ef03a677de47b5283a362ea8f59122f153eb9ca9 +size 4692669152 diff --git a/MMed-Llama-3-8B.Q5_0.gguf b/MMed-Llama-3-8B.Q5_0.gguf new file mode 100644 index 0000000..9da9cf0 --- /dev/null +++ b/MMed-Llama-3-8B.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de54cea9d82757a294067773c57c1376309b7b4edb9fa89bdf8f7a2fd1bfdd81 +size 5599294176 diff --git a/MMed-Llama-3-8B.Q5_1.gguf b/MMed-Llama-3-8B.Q5_1.gguf new file mode 100644 index 0000000..75913e4 --- /dev/null +++ b/MMed-Llama-3-8B.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91b53f423e5342944000d29f1df10fee3684878c2c419f4c57218c9f4fa2a78c +size 6068335328 diff --git a/MMed-Llama-3-8B.Q5_K_M.gguf b/MMed-Llama-3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..447d9f0 --- /dev/null +++ b/MMed-Llama-3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fe7ae13e4dc7d328ec48d05bd8c6d653e979c152d835943cb97b97e0ff5ada1 +size 5732987616 diff --git a/MMed-Llama-3-8B.Q5_K_S.gguf b/MMed-Llama-3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..68d3671 --- /dev/null +++ b/MMed-Llama-3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:305553e0ccbdd61bcb8474a7d1bdab06f7e633584bb979580b0576f81df385d8 +size 5599294176 diff --git a/MMed-Llama-3-8B.Q6_K.gguf b/MMed-Llama-3-8B.Q6_K.gguf new file mode 100644 index 0000000..6a88fcb --- /dev/null +++ b/MMed-Llama-3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0347d814ce9d57c1808126037dfe4d75e741183703093e9dc892a8b93aa07417 +size 6596006624 diff --git a/MMed-Llama-3-8B.Q8_0.gguf b/MMed-Llama-3-8B.Q8_0.gguf new file mode 100644 index 0000000..8dd4a52 --- /dev/null +++ b/MMed-Llama-3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f9c500fa38e033cf096508357de9d5f2af209c4d654627fe3d99139b5e77674 +size 8540771040 diff --git a/README.md b/README.md new file mode 100644 index 0000000..61c1bc3 --- /dev/null +++ b/README.md @@ -0,0 +1,96 @@ + +--- + +license: llama3 +datasets: +- Henrychur/MMedC +language: +- en +- zh +- ja +- fr +- ru +- es +tags: +- medical + +--- + +[![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory) + + +# QuantFactory/MMed-Llama-3-8B-GGUF +This is quantized version of [Henrychur/MMed-Llama-3-8B](https://huggingface.co/Henrychur/MMed-Llama-3-8B) created using llama.cpp + +# Original Model Card + +# MMedLM +[💻Github Repo](https://github.com/MAGIC-AI4Med/MMedLM) [🖨️arXiv Paper](https://arxiv.org/abs/2402.13963) + +The official model weights for "Towards Building Multilingual Language Model for Medicine". + + +## Introduction +This repo contains MMed-Llama 3, a multilingual medical foundation model with 8 billion parameters. MMed-Llama 3 builds upon the foundation of Llama 3 and has been further pretrained on MMedC, a comprehensive multilingual medical corpus. This further pretraining enhances the model's medical-domain knowledge. + +The model underwent further pretraining on MMedC with the following hyperparameters: +- Iterations: 15000 +- Global batch size: 512 +- Cutoff length: 8192 +- Learning rate: 2e-5 + +The model can be loaded as follows: +```py +import torch +from transformers import AutoTokenizer, AutoModelForCausalLM +tokenizer = AutoTokenizer.from_pretrained("Henrychur/MMed-Llama-3-8B") +model = AutoModelForCausalLM.from_pretrained("Henrychur/MMed-Llama-3-8B", torch_dtype=torch.float16) +``` + +- Note that this is a foundation model that has not undergone instruction fine-tuning. +## News +[2024.2.21] Our pre-print paper is released ArXiv. Dive into our findings [here](https://arxiv.org/abs/2402.13963). + +[2024.2.20] We release [MMedLM](https://huggingface.co/Henrychur/MMedLM) and [MMedLM 2](https://huggingface.co/Henrychur/MMedLM2). With an auto-regressive continues training on MMedC, these models achieves superior performance compared to all other open-source models, even rivaling GPT-4 on MMedBench. + +[2023.2.20] We release [MMedC](https://huggingface.co/datasets/Henrychur/MMedC), a multilingual medical corpus containing 25.5B tokens. + +[2023.2.20] We release [MMedBench](https://huggingface.co/datasets/Henrychur/MMedBench), a new multilingual medical multi-choice question-answering +benchmark with rationale. Check out the leaderboard [here](https://henrychur.github.io/MultilingualMedQA/). + +## Evaluation on MMedBench +The further pretrained MMedLM 2 showcast it's great performance in medical domain across different language. + +| Method | Size | Year | MMedC | MMedBench | English | Chinese | Japanese | French | Russian | Spanish | Avg. | +|------------------|------|---------|-----------|-----------|----------------|----------------|----------------|----------------|----------------|----------------|----------------| +| GPT-3.5 | - | 2022.12 | ✗ | ✗ | 56.88 | 52.29 | 34.63 | 32.48 | 66.36 | 66.06 | 51.47 | +| GPT-4 | - | 2023.3 | ✗ | ✗ | 78.00 | 75.07 | 72.91 | 56.59 | 83.62 | 85.67 | 74.27 | +| Gemini-1.0 pro | - | 2024.1 | ✗ | ✗ | 53.73 | 60.19 | 44.22 | 29.90 | 73.44 | 69.69 | 55.20 | +| BLOOMZ | 7B | 2023.5 | ✗ | trainset | 43.28 | 58.06 | 32.66 | 26.37 | 62.89 | 47.34 | 45.10 | +| InternLM | 7B | 2023.7 | ✗ | trainset | 44.07 | 64.62 | 37.19 | 24.92 | 58.20 | 44.97 | 45.67 | +| Llama 2 | 7B | 2023.7 | ✗ | trainset | 43.36 | 50.29 | 25.13 | 20.90 | 66.80 | 47.10 | 42.26 | +| MedAlpaca | 7B | 2023.3 | ✗ | trainset | 46.74 | 44.80 | 29.64 | 21.06 | 59.38 | 45.00 | 41.11 | +| ChatDoctor | 7B | 2023.4 | ✗ | trainset | 43.52 | 43.26 | 25.63 | 18.81 | 62.50 | 43.44 | 39.53 | +| PMC-LLaMA | 7B | 2023.4 | ✗ | trainset | 47.53 | 42.44 | 24.12 | 20.74 | 62.11 | 43.29 | 40.04 | +| Mistral | 7B | 2023.10 | ✗ | trainset | 61.74 | 71.10 | 44.72 | 48.71 | 74.22 | 63.86 | 60.73 | +| InternLM 2 | 7B | 2024.2 | ✗ | trainset | 57.27 | 77.55 | 47.74 | 41.00 | 68.36 | 59.59 | 58.59 | +| MMedLM(Ours) | 7B | - | ✓ | trainset | 49.88 | 70.49 | 46.23 | 36.66 | 72.27 | 54.52 | 55.01 | +| MMedLM 2(Ours) | 7B | - | ✓ | trainset | 61.74 | 80.01 | 61.81 | 52.09 | 80.47 | 67.65 | 67.30 | +|MMed-Llama 3(Ours)|8B |- | ✓ | trainset | 66.06| 79.25 | 61.81 | 55.63 | 75.39 | 68.38 | 67.75 | +- GPT and Gemini is evluated under zero-shot setting through API +- Open-source models first undergo training on the trainset of MMedBench before evaluate. + +## Contact +If you have any question, please feel free to contact qiupengcheng@pjlab.org.cn. + +## Citation +``` +@misc{qiu2024building, + title={Towards Building Multilingual Language Model for Medicine}, + author={Pengcheng Qiu and Chaoyi Wu and Xiaoman Zhang and Weixiong Lin and Haicheng Wang and Ya Zhang and Yanfeng Wang and Weidi Xie}, + year={2024}, + eprint={2402.13963}, + archivePrefix={arXiv}, + primaryClass={cs.CL} +} +``` 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