commit 16a2cae8acab3aeaf8f43162915bf8bd5127eee0 Author: ModelHub XC Date: Thu Sep 10 08:02:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-Clin-REACT-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e2c6f0b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +Llama-Clin-REACT-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Clin-REACT-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Clin-REACT-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Clin-REACT-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Clin-REACT-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Clin-REACT-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Clin-REACT-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Clin-REACT-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Clin-REACT-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Clin-REACT-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Clin-REACT-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Clin-REACT-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-Clin-REACT-8B.IQ4_XS.gguf b/Llama-Clin-REACT-8B.IQ4_XS.gguf new file mode 100644 index 0000000..e1a87d8 --- /dev/null +++ b/Llama-Clin-REACT-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:376741aa2b796f91001d0d17403644c36a75add225cb6f9caa07c110d2b384cf +size 4484368608 diff --git a/Llama-Clin-REACT-8B.Q2_K.gguf b/Llama-Clin-REACT-8B.Q2_K.gguf new file mode 100644 index 0000000..906a606 --- /dev/null +++ b/Llama-Clin-REACT-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:432e223126e78bb5409d912fe514860f698edad12a9cfb58216adebacb7d7146 +size 3179137248 diff --git a/Llama-Clin-REACT-8B.Q3_K_L.gguf b/Llama-Clin-REACT-8B.Q3_K_L.gguf new file mode 100644 index 0000000..ade2e49 --- /dev/null +++ b/Llama-Clin-REACT-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c78d91f4d42470683af84d3dd9c4e8cac291a3072ab4427aa4a79d8e4f7d7d1 +size 4321962208 diff --git a/Llama-Clin-REACT-8B.Q3_K_M.gguf b/Llama-Clin-REACT-8B.Q3_K_M.gguf new file mode 100644 index 0000000..45a24cd --- /dev/null +++ b/Llama-Clin-REACT-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1c779b1dd1845cedd2990b764ec3c600d760df1c04b014e59b5623d1136688f +size 4018923744 diff --git a/Llama-Clin-REACT-8B.Q3_K_S.gguf b/Llama-Clin-REACT-8B.Q3_K_S.gguf new file mode 100644 index 0000000..c14624d --- /dev/null +++ b/Llama-Clin-REACT-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b854a8ddc4e638c12b7f9220d391992a67fda10be5f10d4e5a1a7dcd102d4107 +size 3664505056 diff --git a/Llama-Clin-REACT-8B.Q4_K_M.gguf b/Llama-Clin-REACT-8B.Q4_K_M.gguf new file mode 100644 index 0000000..c8ebfa6 --- /dev/null +++ b/Llama-Clin-REACT-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f231098e29ae02a192a472e1d3c52c3e54ba16cb996c4f017831e4911b71033 +size 4920740064 diff --git a/Llama-Clin-REACT-8B.Q4_K_S.gguf b/Llama-Clin-REACT-8B.Q4_K_S.gguf new file mode 100644 index 0000000..1a9090c --- /dev/null +++ b/Llama-Clin-REACT-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64d39231d01dc630baa8699fb28dc245ae5dcdc102769abb50ab3dba28d7e29b +size 4692674784 diff --git a/Llama-Clin-REACT-8B.Q5_K_M.gguf b/Llama-Clin-REACT-8B.Q5_K_M.gguf new file mode 100644 index 0000000..d1384ee --- /dev/null +++ b/Llama-Clin-REACT-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc68ea9294662748792b2aa9d879ac77986fddf3851a3177eb7b26ce930196f3 +size 5732993248 diff --git a/Llama-Clin-REACT-8B.Q5_K_S.gguf b/Llama-Clin-REACT-8B.Q5_K_S.gguf new file mode 100644 index 0000000..a8802bf --- /dev/null +++ b/Llama-Clin-REACT-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78f907d7bbab665d541bcd054ccd207380b9561ab4e55fbe1ad5e5f83316129f +size 5599299808 diff --git a/Llama-Clin-REACT-8B.Q6_K.gguf b/Llama-Clin-REACT-8B.Q6_K.gguf new file mode 100644 index 0000000..8b688dc --- /dev/null +++ b/Llama-Clin-REACT-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:661b324780451fbe915f1d1d35b9b4f2f1ce1880faed8a666b7777248aeea165 +size 6596012256 diff --git a/Llama-Clin-REACT-8B.Q8_0.gguf b/Llama-Clin-REACT-8B.Q8_0.gguf new file mode 100644 index 0000000..ba2bc63 --- /dev/null +++ b/Llama-Clin-REACT-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0061b09a790f58072fe7baa286fa8b2b12cf63984a34a57afde6c71ad930856c +size 8540776672 diff --git a/Llama-Clin-REACT-8B.f16.gguf b/Llama-Clin-REACT-8B.f16.gguf new file mode 100644 index 0000000..07a0c3d --- /dev/null +++ b/Llama-Clin-REACT-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ea793fd7a94060b767bd693173a9aa4950d81e535b79892b1b4ea2a6574cb70 +size 16068896992 diff --git a/README.md b/README.md new file mode 100644 index 0000000..70bece7 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: iheallab/Llama-Clin-REACT-8B +datasets: +- macontreras98/ICU-REACT +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama +- llama-3.1 +- clinical +- medical +- clinical-reasoning +- icu +- clin-react +--- +## About + + + + + + + + + +static quants of https://huggingface.co/iheallab/Llama-Clin-REACT-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-Clin-REACT-8B-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Llama-Clin-REACT-8B-GGUF/resolve/main/Llama-Clin-REACT-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Clin-REACT-8B-GGUF/resolve/main/Llama-Clin-REACT-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Clin-REACT-8B-GGUF/resolve/main/Llama-Clin-REACT-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Clin-REACT-8B-GGUF/resolve/main/Llama-Clin-REACT-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Clin-REACT-8B-GGUF/resolve/main/Llama-Clin-REACT-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Clin-REACT-8B-GGUF/resolve/main/Llama-Clin-REACT-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Clin-REACT-8B-GGUF/resolve/main/Llama-Clin-REACT-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Clin-REACT-8B-GGUF/resolve/main/Llama-Clin-REACT-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Clin-REACT-8B-GGUF/resolve/main/Llama-Clin-REACT-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Clin-REACT-8B-GGUF/resolve/main/Llama-Clin-REACT-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Clin-REACT-8B-GGUF/resolve/main/Llama-Clin-REACT-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Clin-REACT-8B-GGUF/resolve/main/Llama-Clin-REACT-8B.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +