commit 381efe712b59ecab7880e21205478bea2f274560 Author: ModelHub XC Date: Thu Jun 4 15:19:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GPT2-medical-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1bd65a2 --- /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 +GPT2-medical.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-medical.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-medical.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-medical.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-medical.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-medical.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-medical.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-medical.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-medical.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-medical.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-medical.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-medical.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GPT2-medical.IQ4_XS.gguf b/GPT2-medical.IQ4_XS.gguf new file mode 100644 index 0000000..9fce04f --- /dev/null +++ b/GPT2-medical.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5eb829da98eca9a634344ad9dfd120709a5f39e21cfe0328e441576e67544b2 +size 103063712 diff --git a/GPT2-medical.Q2_K.gguf b/GPT2-medical.Q2_K.gguf new file mode 100644 index 0000000..6f63c59 --- /dev/null +++ b/GPT2-medical.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a13f1f3e841cfdc4b52249baca0ff9ec7a8fe009635776da8d79d126d86b1ea5 +size 81196864 diff --git a/GPT2-medical.Q3_K_L.gguf b/GPT2-medical.Q3_K_L.gguf new file mode 100644 index 0000000..34e07c0 --- /dev/null +++ b/GPT2-medical.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dabef1abc0d81743a43713d6ccc8a766d5e4114e8385d75c5158b7a83b615c0 +size 102092800 diff --git a/GPT2-medical.Q3_K_M.gguf b/GPT2-medical.Q3_K_M.gguf new file mode 100644 index 0000000..a4db743 --- /dev/null +++ b/GPT2-medical.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cd4542b67a127bad80f4e7722af23f4bbccf3b8f518f7745b504ac191a90b38 +size 97669120 diff --git a/GPT2-medical.Q3_K_S.gguf b/GPT2-medical.Q3_K_S.gguf new file mode 100644 index 0000000..4e27ddd --- /dev/null +++ b/GPT2-medical.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4de3c6f815d02633740c75a5a3c9f6c8d65a1304f05646a96b4cb88807dc5ba4 +size 90148864 diff --git a/GPT2-medical.Q4_K_M.gguf b/GPT2-medical.Q4_K_M.gguf new file mode 100644 index 0000000..c529230 --- /dev/null +++ b/GPT2-medical.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f227587b274b255c3734a64d7f88a26f39237ef3b3ff2fb48d2ec1b2c1945a12 +size 112859200 diff --git a/GPT2-medical.Q4_K_S.gguf b/GPT2-medical.Q4_K_S.gguf new file mode 100644 index 0000000..14439d6 --- /dev/null +++ b/GPT2-medical.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ee326af28d16968f67ac2d7f034d88faed4ab050f2e11555c37d0e300d5e7d9 +size 106850368 diff --git a/GPT2-medical.Q5_K_M.gguf b/GPT2-medical.Q5_K_M.gguf new file mode 100644 index 0000000..98fe2cf --- /dev/null +++ b/GPT2-medical.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd86c6f25a0d26751df428aced54a9b185d304810164bb8159073199d2b68992 +size 126697120 diff --git a/GPT2-medical.Q5_K_S.gguf b/GPT2-medical.Q5_K_S.gguf new file mode 100644 index 0000000..576450d --- /dev/null +++ b/GPT2-medical.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c74d1b29977c954bcd1587e27e87276def058a6a1d7c5d91ab7feb9988f626d2 +size 121996960 diff --git a/GPT2-medical.Q6_K.gguf b/GPT2-medical.Q6_K.gguf new file mode 100644 index 0000000..bef1d3a --- /dev/null +++ b/GPT2-medical.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7f51e42bdf998d2f195a9027e8ab050dac2a7d73b5fac96c690c968828e3c39 +size 138403552 diff --git a/GPT2-medical.Q8_0.gguf b/GPT2-medical.Q8_0.gguf new file mode 100644 index 0000000..03fa420 --- /dev/null +++ b/GPT2-medical.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93fb4a1a9da22e51d95c3d98119d4986cce2e295fa799ac8fd55f001029aae8b +size 177669280 diff --git a/GPT2-medical.f16.gguf b/GPT2-medical.f16.gguf new file mode 100644 index 0000000..b263e21 --- /dev/null +++ b/GPT2-medical.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25a61af254addaffa4724410db47cea50b9794670612d75efa89121c05e3f801 +size 329665568 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b26c254 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Afiqa/GPT2-medical +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/Afiqa/GPT2-medical + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GPT2-medical-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/GPT2-medical-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/GPT2-medical-GGUF/resolve/main/GPT2-medical.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/GPT2-medical-GGUF/resolve/main/GPT2-medical.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/GPT2-medical-GGUF/resolve/main/GPT2-medical.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GPT2-medical-GGUF/resolve/main/GPT2-medical.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/GPT2-medical-GGUF/resolve/main/GPT2-medical.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/GPT2-medical-GGUF/resolve/main/GPT2-medical.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GPT2-medical-GGUF/resolve/main/GPT2-medical.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GPT2-medical-GGUF/resolve/main/GPT2-medical.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/GPT2-medical-GGUF/resolve/main/GPT2-medical.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/GPT2-medical-GGUF/resolve/main/GPT2-medical.Q6_K.gguf) | Q6_K | 0.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GPT2-medical-GGUF/resolve/main/GPT2-medical.Q8_0.gguf) | Q8_0 | 0.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GPT2-medical-GGUF/resolve/main/GPT2-medical.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. + +