commit c3e66bca0bd766ff5f39d732ac75effb58d57370 Author: ModelHub XC Date: Tue Oct 20 09:44:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MedGPT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..40a3657 --- /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 +MedGPT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MedGPT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MedGPT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MedGPT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedGPT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedGPT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedGPT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedGPT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedGPT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedGPT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MedGPT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MedGPT.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MedGPT.IQ4_XS.gguf b/MedGPT.IQ4_XS.gguf new file mode 100644 index 0000000..6a56d42 --- /dev/null +++ b/MedGPT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:044f7370110501ca231a8dc5966c7ad702792c735e4cd9dbed71593257c03e82 +size 103063744 diff --git a/MedGPT.Q2_K.gguf b/MedGPT.Q2_K.gguf new file mode 100644 index 0000000..23bf42c --- /dev/null +++ b/MedGPT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7717a61d4bdb789e346a048a266e7c36d4d60f0a5379728f07b1ee32139bfdfe +size 81196896 diff --git a/MedGPT.Q3_K_L.gguf b/MedGPT.Q3_K_L.gguf new file mode 100644 index 0000000..daa1228 --- /dev/null +++ b/MedGPT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f76f583a6cf927516d4f48e7b604fbe7e511208299ac48791efe2a0189d8aacd +size 102092832 diff --git a/MedGPT.Q3_K_M.gguf b/MedGPT.Q3_K_M.gguf new file mode 100644 index 0000000..92b30f9 --- /dev/null +++ b/MedGPT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5101b8cff83d6fe38052a219d8bf0df6bc20abd9ab9956ebd7bf6a31eb27846 +size 97669152 diff --git a/MedGPT.Q3_K_S.gguf b/MedGPT.Q3_K_S.gguf new file mode 100644 index 0000000..3d5ace4 --- /dev/null +++ b/MedGPT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f7b05b54f862e2eb97a23a1ef591cec144b6cfabff944b7d9eddd2a115623a6 +size 90148896 diff --git a/MedGPT.Q4_K_M.gguf b/MedGPT.Q4_K_M.gguf new file mode 100644 index 0000000..3c19cc4 --- /dev/null +++ b/MedGPT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d59ada6faf85c9c251f8989b1c042ce203a487951088062bf135e195908fde5 +size 112859232 diff --git a/MedGPT.Q4_K_S.gguf b/MedGPT.Q4_K_S.gguf new file mode 100644 index 0000000..79a9a21 --- /dev/null +++ b/MedGPT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f98f10baa0d4e881a9b38f37b788c0c142f45d636cc4f9172d2761814f330a38 +size 106850400 diff --git a/MedGPT.Q5_K_M.gguf b/MedGPT.Q5_K_M.gguf new file mode 100644 index 0000000..fc669b4 --- /dev/null +++ b/MedGPT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06917b69dd4da4ced041fc0b928754e97c437fd76abdaaf5b839640b086de129 +size 126697152 diff --git a/MedGPT.Q5_K_S.gguf b/MedGPT.Q5_K_S.gguf new file mode 100644 index 0000000..d35a11a --- /dev/null +++ b/MedGPT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbf4dab662516c4ac37731ca38b758d6905d100de0f0018ddb2a19c597d48182 +size 121996992 diff --git a/MedGPT.Q6_K.gguf b/MedGPT.Q6_K.gguf new file mode 100644 index 0000000..7279cdc --- /dev/null +++ b/MedGPT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20f1ac93fc694c84a13adcb8cf5b24192ec332adbcebc38af61bad8e1ca68f80 +size 138403584 diff --git a/MedGPT.Q8_0.gguf b/MedGPT.Q8_0.gguf new file mode 100644 index 0000000..01481d0 --- /dev/null +++ b/MedGPT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f41ad210f6fe81c59d01f45bf822b1d48bbc5b3edfa0ada660cdc009446d71d +size 177669312 diff --git a/MedGPT.f16.gguf b/MedGPT.f16.gguf new file mode 100644 index 0000000..ffb8113 --- /dev/null +++ b/MedGPT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e90572e7fac9d5e8d0cfdc653e08f24c2785ab2618bbe15886e8b410e68cb297 +size 329665600 diff --git a/README.md b/README.md new file mode 100644 index 0000000..366d894 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: Rabbiaaa/MedGPT +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/Rabbiaaa/MedGPT + + +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/MedGPT-GGUF/resolve/main/MedGPT.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/MedGPT-GGUF/resolve/main/MedGPT.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/MedGPT-GGUF/resolve/main/MedGPT.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MedGPT-GGUF/resolve/main/MedGPT.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/MedGPT-GGUF/resolve/main/MedGPT.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/MedGPT-GGUF/resolve/main/MedGPT.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MedGPT-GGUF/resolve/main/MedGPT.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MedGPT-GGUF/resolve/main/MedGPT.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/MedGPT-GGUF/resolve/main/MedGPT.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/MedGPT-GGUF/resolve/main/MedGPT.Q6_K.gguf) | Q6_K | 0.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MedGPT-GGUF/resolve/main/MedGPT.Q8_0.gguf) | Q8_0 | 0.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MedGPT-GGUF/resolve/main/MedGPT.f16.gguf) | f16 | 0.4 | 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. + +