commit 933cbca57ccd626eb820a2e0597a67be732cdcd7 Author: ModelHub XC Date: Wed Jun 10 19:18:18 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/MediPhi-PubMed-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1888393 --- /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 +MediPhi-PubMed.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MediPhi-PubMed.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MediPhi-PubMed.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MediPhi-PubMed.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MediPhi-PubMed.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MediPhi-PubMed.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MediPhi-PubMed.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MediPhi-PubMed.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MediPhi-PubMed.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MediPhi-PubMed.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MediPhi-PubMed.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MediPhi-PubMed.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MediPhi-PubMed.IQ4_XS.gguf b/MediPhi-PubMed.IQ4_XS.gguf new file mode 100644 index 0000000..a837efd --- /dev/null +++ b/MediPhi-PubMed.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acef45af183d9edba8a8aa614222e395bc2e90a7b99b9dce93d39491d02e4641 +size 2075582176 diff --git a/MediPhi-PubMed.Q2_K.gguf b/MediPhi-PubMed.Q2_K.gguf new file mode 100644 index 0000000..226f711 --- /dev/null +++ b/MediPhi-PubMed.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7464e94df3dfdb1eeb9472f70b456111e8c9e80236eb8cf6fbe1fa2acb23050c +size 1416205024 diff --git a/MediPhi-PubMed.Q3_K_L.gguf b/MediPhi-PubMed.Q3_K_L.gguf new file mode 100644 index 0000000..239ed7b --- /dev/null +++ b/MediPhi-PubMed.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dc52683516140ea886cb905dd39ddddf4dde984d50a138f48489c0ba49dbd40 +size 2087598304 diff --git a/MediPhi-PubMed.Q3_K_M.gguf b/MediPhi-PubMed.Q3_K_M.gguf new file mode 100644 index 0000000..e10ab9f --- /dev/null +++ b/MediPhi-PubMed.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87d7ed0924c3a95f74c0de276e8478b9e4d7f2e03e69a5900fc673a726de674d +size 1955477728 diff --git a/MediPhi-PubMed.Q3_K_S.gguf b/MediPhi-PubMed.Q3_K_S.gguf new file mode 100644 index 0000000..a7a8598 --- /dev/null +++ b/MediPhi-PubMed.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:024e567d71caf6ace01f6a6d572dd135e57b1b54bc6b9d9b90e451d7d6e6c23d +size 1681799392 diff --git a/MediPhi-PubMed.Q4_K_M.gguf b/MediPhi-PubMed.Q4_K_M.gguf new file mode 100644 index 0000000..59913df --- /dev/null +++ b/MediPhi-PubMed.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfcf4e9c67f78ced59259a1d2cce05c2d03bcdd80d26c364f9d8cf286c96ff72 +size 2393233120 diff --git a/MediPhi-PubMed.Q4_K_S.gguf b/MediPhi-PubMed.Q4_K_S.gguf new file mode 100644 index 0000000..7bf4912 --- /dev/null +++ b/MediPhi-PubMed.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:619e1cbc875df6dcbb309f6c5262b357db00084211898c9d5d3f361092591304 +size 2188760800 diff --git a/MediPhi-PubMed.Q5_K_M.gguf b/MediPhi-PubMed.Q5_K_M.gguf new file mode 100644 index 0000000..23e6cb0 --- /dev/null +++ b/MediPhi-PubMed.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:883a7cc32ae84178ea6e920b9252e0e61a661fbfb6f1f32aa9e5c66ccc11decc +size 2815276768 diff --git a/MediPhi-PubMed.Q5_K_S.gguf b/MediPhi-PubMed.Q5_K_S.gguf new file mode 100644 index 0000000..be4e6d3 --- /dev/null +++ b/MediPhi-PubMed.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddeddd3c06ae5c2a0e0ef744c346f2cb4792ea5852a2e13cd9909e1852dcb9a5 +size 2641475296 diff --git a/MediPhi-PubMed.Q6_K.gguf b/MediPhi-PubMed.Q6_K.gguf new file mode 100644 index 0000000..9c1c691 --- /dev/null +++ b/MediPhi-PubMed.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9238eed4a81a6b72ecc226d8d3ca082b2ea68efdc835d6c364be2a07212ff5ac +size 3135853792 diff --git a/MediPhi-PubMed.Q8_0.gguf b/MediPhi-PubMed.Q8_0.gguf new file mode 100644 index 0000000..33effd8 --- /dev/null +++ b/MediPhi-PubMed.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2ce1c4db5cb253134de5193f84cf5d5cdc8bdd5b4e5f751ffce5563eff5cfca +size 4061223136 diff --git a/MediPhi-PubMed.f16.gguf b/MediPhi-PubMed.f16.gguf new file mode 100644 index 0000000..d5e9e46 --- /dev/null +++ b/MediPhi-PubMed.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24b7407b92e5fec045b488a82e0edb86fd1d8ec0f755a4019e2c3c948ab6fe72 +size 7643298016 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9da33e3 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: microsoft/MediPhi-PubMed +datasets: +- ncbi/pubmed +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- mergekit +- medical +- clinical +--- +## About + + + + + + +static quants of https://huggingface.co/microsoft/MediPhi-PubMed + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MediPhi-PubMed-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/MediPhi-PubMed-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/MediPhi-PubMed-GGUF/resolve/main/MediPhi-PubMed.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/MediPhi-PubMed-GGUF/resolve/main/MediPhi-PubMed.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/MediPhi-PubMed-GGUF/resolve/main/MediPhi-PubMed.Q3_K_M.gguf) | Q3_K_M | 2.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MediPhi-PubMed-GGUF/resolve/main/MediPhi-PubMed.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/MediPhi-PubMed-GGUF/resolve/main/MediPhi-PubMed.Q3_K_L.gguf) | Q3_K_L | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/MediPhi-PubMed-GGUF/resolve/main/MediPhi-PubMed.Q4_K_S.gguf) | Q4_K_S | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MediPhi-PubMed-GGUF/resolve/main/MediPhi-PubMed.Q4_K_M.gguf) | Q4_K_M | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MediPhi-PubMed-GGUF/resolve/main/MediPhi-PubMed.Q5_K_S.gguf) | Q5_K_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/MediPhi-PubMed-GGUF/resolve/main/MediPhi-PubMed.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/MediPhi-PubMed-GGUF/resolve/main/MediPhi-PubMed.Q6_K.gguf) | Q6_K | 3.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MediPhi-PubMed-GGUF/resolve/main/MediPhi-PubMed.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MediPhi-PubMed-GGUF/resolve/main/MediPhi-PubMed.f16.gguf) | f16 | 7.7 | 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. + +