commit dc063db69e44082a533b361c4c3fc91a94461dcd Author: ModelHub XC Date: Thu Jun 4 15:31:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/finetuned-gpt2-medical-model-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..061e91b --- /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 +finetuned-gpt2-medical-model.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +finetuned-gpt2-medical-model.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +finetuned-gpt2-medical-model.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +finetuned-gpt2-medical-model.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +finetuned-gpt2-medical-model.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +finetuned-gpt2-medical-model.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +finetuned-gpt2-medical-model.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +finetuned-gpt2-medical-model.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +finetuned-gpt2-medical-model.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +finetuned-gpt2-medical-model.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +finetuned-gpt2-medical-model.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +finetuned-gpt2-medical-model.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..3d9cdd8 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: himanshu16/finetuned-gpt2-medical-model +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/himanshu16/finetuned-gpt2-medical-model + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#finetuned-gpt2-medical-model-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/finetuned-gpt2-medical-model-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/finetuned-gpt2-medical-model-GGUF/resolve/main/finetuned-gpt2-medical-model.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/finetuned-gpt2-medical-model-GGUF/resolve/main/finetuned-gpt2-medical-model.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/finetuned-gpt2-medical-model-GGUF/resolve/main/finetuned-gpt2-medical-model.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/finetuned-gpt2-medical-model-GGUF/resolve/main/finetuned-gpt2-medical-model.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/finetuned-gpt2-medical-model-GGUF/resolve/main/finetuned-gpt2-medical-model.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/finetuned-gpt2-medical-model-GGUF/resolve/main/finetuned-gpt2-medical-model.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/finetuned-gpt2-medical-model-GGUF/resolve/main/finetuned-gpt2-medical-model.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/finetuned-gpt2-medical-model-GGUF/resolve/main/finetuned-gpt2-medical-model.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/finetuned-gpt2-medical-model-GGUF/resolve/main/finetuned-gpt2-medical-model.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/finetuned-gpt2-medical-model-GGUF/resolve/main/finetuned-gpt2-medical-model.Q6_K.gguf) | Q6_K | 0.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/finetuned-gpt2-medical-model-GGUF/resolve/main/finetuned-gpt2-medical-model.Q8_0.gguf) | Q8_0 | 0.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/finetuned-gpt2-medical-model-GGUF/resolve/main/finetuned-gpt2-medical-model.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. + + diff --git a/finetuned-gpt2-medical-model.IQ4_XS.gguf b/finetuned-gpt2-medical-model.IQ4_XS.gguf new file mode 100644 index 0000000..fb53d13 --- /dev/null +++ b/finetuned-gpt2-medical-model.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd6e58942bd6a5c9c8d0d691ae5c2a9232fccd5f3fbcf149b066bba72dbd79a7 +size 103063744 diff --git a/finetuned-gpt2-medical-model.Q2_K.gguf b/finetuned-gpt2-medical-model.Q2_K.gguf new file mode 100644 index 0000000..3b91247 --- /dev/null +++ b/finetuned-gpt2-medical-model.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a5232a2d29095b92db76f6daa6b99858e3947b95ae83385fcab623892621334 +size 81196896 diff --git a/finetuned-gpt2-medical-model.Q3_K_L.gguf b/finetuned-gpt2-medical-model.Q3_K_L.gguf new file mode 100644 index 0000000..b610e5f --- /dev/null +++ b/finetuned-gpt2-medical-model.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74319789365754c26cfb008d0aa6ab4281f97027d9ee8805246d1939a925b283 +size 102092832 diff --git a/finetuned-gpt2-medical-model.Q3_K_M.gguf b/finetuned-gpt2-medical-model.Q3_K_M.gguf new file mode 100644 index 0000000..ff11f50 --- /dev/null +++ b/finetuned-gpt2-medical-model.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88c816d609beeae302afa03b8a37804896cd152a7bad0649372df00661a487cd +size 97669152 diff --git a/finetuned-gpt2-medical-model.Q3_K_S.gguf b/finetuned-gpt2-medical-model.Q3_K_S.gguf new file mode 100644 index 0000000..08f2240 --- /dev/null +++ b/finetuned-gpt2-medical-model.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7ab518fc931791b6ef0d1517c06f71c807e8ed578f0eefcb54e87896dd0384f +size 90148896 diff --git a/finetuned-gpt2-medical-model.Q4_K_M.gguf b/finetuned-gpt2-medical-model.Q4_K_M.gguf new file mode 100644 index 0000000..2d0c865 --- /dev/null +++ b/finetuned-gpt2-medical-model.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2ccc1323c175c996b7cafdeebe9a3294e6f418e5f206b7f29e880da8c0a6b8a +size 112859232 diff --git a/finetuned-gpt2-medical-model.Q4_K_S.gguf b/finetuned-gpt2-medical-model.Q4_K_S.gguf new file mode 100644 index 0000000..d83acd3 --- /dev/null +++ b/finetuned-gpt2-medical-model.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c12c189055b55ce064a06eca75ab2a8b73f14983c2c17d239ca159a236bcd9a +size 106850400 diff --git a/finetuned-gpt2-medical-model.Q5_K_M.gguf b/finetuned-gpt2-medical-model.Q5_K_M.gguf new file mode 100644 index 0000000..fad6146 --- /dev/null +++ b/finetuned-gpt2-medical-model.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62e25fc042b3ba6d81ff61242331e4fa9e3d6fe2244d3002a648a4e4e5b27eaa +size 126697152 diff --git a/finetuned-gpt2-medical-model.Q5_K_S.gguf b/finetuned-gpt2-medical-model.Q5_K_S.gguf new file mode 100644 index 0000000..2229a36 --- /dev/null +++ b/finetuned-gpt2-medical-model.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8130d87f143188fbc0ee1b36cadca88b853c2e9779a4f6233b2b6fc68d05478d +size 121996992 diff --git a/finetuned-gpt2-medical-model.Q6_K.gguf b/finetuned-gpt2-medical-model.Q6_K.gguf new file mode 100644 index 0000000..b23d233 --- /dev/null +++ b/finetuned-gpt2-medical-model.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a1cb70509d02a3e1aa9502070c092c2889dad305161c0d4a8b1b0e7fc48b66b +size 138403584 diff --git a/finetuned-gpt2-medical-model.Q8_0.gguf b/finetuned-gpt2-medical-model.Q8_0.gguf new file mode 100644 index 0000000..c205e23 --- /dev/null +++ b/finetuned-gpt2-medical-model.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e2db6fb491ad83ee2c761e9d73cd043b479a016691a97c9cc6bac6e6adf957a +size 177669312 diff --git a/finetuned-gpt2-medical-model.f16.gguf b/finetuned-gpt2-medical-model.f16.gguf new file mode 100644 index 0000000..5a5e7b9 --- /dev/null +++ b/finetuned-gpt2-medical-model.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a716f3c348385c8e43d2741a36610b3986b10dc1763733ed5fb16c66f01e0a2 +size 329665600