commit d1416a1a031bf0e76ef1831d1e87b9386cadd6b9 Author: ModelHub XC Date: Mon Aug 10 17:35:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LlamaMed-3.1-8B-Reasoner-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d8eabf2 --- /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 +LlamaMed-3.1-8B-Reasoner.f16.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LlamaMed-3.1-8B-Reasoner.IQ4_XS.gguf b/LlamaMed-3.1-8B-Reasoner.IQ4_XS.gguf new file mode 100644 index 0000000..40b4edd --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8251e44673eda7bd68fbd631c48d93d7e8d33e5536b1305f1c09a35dd3145b74 +size 4484368736 diff --git a/LlamaMed-3.1-8B-Reasoner.Q2_K.gguf b/LlamaMed-3.1-8B-Reasoner.Q2_K.gguf new file mode 100644 index 0000000..2e13a58 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae882cd3701e426e38c6f98cbb1a642610780b713fdca7cb9e927b615a533290 +size 3179137376 diff --git a/LlamaMed-3.1-8B-Reasoner.Q3_K_L.gguf b/LlamaMed-3.1-8B-Reasoner.Q3_K_L.gguf new file mode 100644 index 0000000..10aa041 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:880f0042cb7e4d612c0aaa9ddf6cfbe70ea5808cbf50ac476440f84a3bdaf958 +size 4321962336 diff --git a/LlamaMed-3.1-8B-Reasoner.Q3_K_M.gguf b/LlamaMed-3.1-8B-Reasoner.Q3_K_M.gguf new file mode 100644 index 0000000..97467e4 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5c607d399f97c809bda75c180239bf5718fb95e94234e1bac0cf0a99b280947 +size 4018923872 diff --git a/LlamaMed-3.1-8B-Reasoner.Q3_K_S.gguf b/LlamaMed-3.1-8B-Reasoner.Q3_K_S.gguf new file mode 100644 index 0000000..a334eb9 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8e453d7501ce573309ed11c4403ea87431dd03670b74ab1d20862f053c20be7 +size 3664505184 diff --git a/LlamaMed-3.1-8B-Reasoner.Q4_K_M.gguf b/LlamaMed-3.1-8B-Reasoner.Q4_K_M.gguf new file mode 100644 index 0000000..cac84dc --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a289bfc9aa0e8e3deefaf50e4e8585c5610d865ed732ad84e058ad52807069ca +size 4920740192 diff --git a/LlamaMed-3.1-8B-Reasoner.Q4_K_S.gguf b/LlamaMed-3.1-8B-Reasoner.Q4_K_S.gguf new file mode 100644 index 0000000..9884d33 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c464d7d7b9ab69c6d0bf523e6e988f68b296258467c54c10efd2ed290ecb8cb +size 4692674912 diff --git a/LlamaMed-3.1-8B-Reasoner.Q5_K_M.gguf b/LlamaMed-3.1-8B-Reasoner.Q5_K_M.gguf new file mode 100644 index 0000000..438e00b --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12a875c59457641679d5c2ddaec04caf2f252902b357f49ea7efed4c2f23ebef +size 5732993376 diff --git a/LlamaMed-3.1-8B-Reasoner.Q5_K_S.gguf b/LlamaMed-3.1-8B-Reasoner.Q5_K_S.gguf new file mode 100644 index 0000000..f4cf032 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca3fbc2b8fd279c076ca9c9bcda6cd70bbb281ef962074c9580fb1fc589a28da +size 5599299936 diff --git a/LlamaMed-3.1-8B-Reasoner.Q6_K.gguf b/LlamaMed-3.1-8B-Reasoner.Q6_K.gguf new file mode 100644 index 0000000..2e099fe --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d0795c0f0dd87b1f7a1afe9cbf85a176335228c92cfdd75fd6edd3285f993ba +size 6596012384 diff --git a/LlamaMed-3.1-8B-Reasoner.Q8_0.gguf b/LlamaMed-3.1-8B-Reasoner.Q8_0.gguf new file mode 100644 index 0000000..a3a6ba4 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:521fad65c4d504adff9e0761474214bf8e2b13aca0cffbf772a2b52be1d79b88 +size 8540776800 diff --git a/LlamaMed-3.1-8B-Reasoner.f16.gguf b/LlamaMed-3.1-8B-Reasoner.f16.gguf new file mode 100644 index 0000000..2c0e71b --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ea3bd3d5eaa98e17df2c3a4951fe04ef4c614517b2b70e5e52338679db202a0 +size 16068897120 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2f96198 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: Rumiii/LlamaMed-3.1-8B-Reasoner +datasets: +- lingshu-medical-mllm/ReasonMed +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- medical +- reasoning +- llama-3.1 +- reasonmed +- chain-of-thought +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Rumiii/LlamaMed-3.1-8B-Reasoner + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LlamaMed-3.1-8B-Reasoner-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF +## 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/LlamaMed-3.1-8B-Reasoner-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.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. + +