commit c349ef48a05b1c3d5b0e608811405c80e5977c51 Author: ModelHub XC Date: Fri May 1 07:40:34 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MedGemma-GRPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e04e3a1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +MedGemma-GRPO.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MedGemma-GRPO.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +MedGemma-GRPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MedGemma-GRPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MedGemma-GRPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MedGemma-GRPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedGemma-GRPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedGemma-GRPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedGemma-GRPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedGemma-GRPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedGemma-GRPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedGemma-GRPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MedGemma-GRPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MedGemma-GRPO.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MedGemma-GRPO.IQ4_XS.gguf b/MedGemma-GRPO.IQ4_XS.gguf new file mode 100644 index 0000000..3e76cac --- /dev/null +++ b/MedGemma-GRPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f2c64f3d5f4822152c31b3afac78686bbdc5ee1858809475768f1305a5f5c88 +size 2279626592 diff --git a/MedGemma-GRPO.Q2_K.gguf b/MedGemma-GRPO.Q2_K.gguf new file mode 100644 index 0000000..7ce236d --- /dev/null +++ b/MedGemma-GRPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3223869876dd7996dd52f789c16a6d925105d178cc0f432e81e2a4294e6bf61 +size 1729165152 diff --git a/MedGemma-GRPO.Q3_K_L.gguf b/MedGemma-GRPO.Q3_K_L.gguf new file mode 100644 index 0000000..0b0e2f7 --- /dev/null +++ b/MedGemma-GRPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a97ed39c51009644e2d4ab280344712577f77fb9062982306d6815d41e78296c +size 2236086112 diff --git a/MedGemma-GRPO.Q3_K_M.gguf b/MedGemma-GRPO.Q3_K_M.gguf new file mode 100644 index 0000000..de97cb7 --- /dev/null +++ b/MedGemma-GRPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a883932ba4ad6a00b1d634eb976059692169a82004d4e3f0dbf859d9497ba868 +size 2098460512 diff --git a/MedGemma-GRPO.Q3_K_S.gguf b/MedGemma-GRPO.Q3_K_S.gguf new file mode 100644 index 0000000..e58966b --- /dev/null +++ b/MedGemma-GRPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:864dff102a730ba42ddc10224a47d063bb7937fd7f04a8b73843943fb48ff8bb +size 1937364832 diff --git a/MedGemma-GRPO.Q4_K_M.gguf b/MedGemma-GRPO.Q4_K_M.gguf new file mode 100644 index 0000000..e71c280 --- /dev/null +++ b/MedGemma-GRPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dab6a62ec975e21cadcfbca57de3ad9b41d133e528538bcfed9078fd4ae44d63 +size 2489894752 diff --git a/MedGemma-GRPO.Q4_K_S.gguf b/MedGemma-GRPO.Q4_K_S.gguf new file mode 100644 index 0000000..74e0be8 --- /dev/null +++ b/MedGemma-GRPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5077ab1620243e3e8e33078ca2ac6d2a66eb4b8a9b228d1e6b8697fa6e523add +size 2377930592 diff --git a/MedGemma-GRPO.Q5_K_M.gguf b/MedGemma-GRPO.Q5_K_M.gguf new file mode 100644 index 0000000..e6ffe92 --- /dev/null +++ b/MedGemma-GRPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73a5ec7443471dcc42658e2aa646d32dc39fe7fc9304a6a8b0c85da306657766 +size 2829698912 diff --git a/MedGemma-GRPO.Q5_K_S.gguf b/MedGemma-GRPO.Q5_K_S.gguf new file mode 100644 index 0000000..063d6f9 --- /dev/null +++ b/MedGemma-GRPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6c4e265a7810d61df5626f30ad3da92853e6482d830dd50c2c207c4de93726e +size 2764592992 diff --git a/MedGemma-GRPO.Q6_K.gguf b/MedGemma-GRPO.Q6_K.gguf new file mode 100644 index 0000000..7a95f97 --- /dev/null +++ b/MedGemma-GRPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d235817c87517cb5be8cd103d32f2b4a4f9027482f97af6629352217cf22067c +size 3190740832 diff --git a/MedGemma-GRPO.Q8_0.gguf b/MedGemma-GRPO.Q8_0.gguf new file mode 100644 index 0000000..0bcc51e --- /dev/null +++ b/MedGemma-GRPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbb699d61f202b1f4c247fed0088cc1ba110a721124672c49ed93e2875b37b55 +size 4130402912 diff --git a/MedGemma-GRPO.f16.gguf b/MedGemma-GRPO.f16.gguf new file mode 100644 index 0000000..aa8fa74 --- /dev/null +++ b/MedGemma-GRPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cff4ba8e6b9a6c65e157af7374fdd12618713beb37814e5b6449744c4c6d2f5e +size 7767804512 diff --git a/MedGemma-GRPO.mmproj-Q8_0.gguf b/MedGemma-GRPO.mmproj-Q8_0.gguf new file mode 100644 index 0000000..4dab824 --- /dev/null +++ b/MedGemma-GRPO.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edd300fd1ba2aba03a3e89c03541143591b01e1613f56a5d8394ab717d73b85f +size 591378016 diff --git a/MedGemma-GRPO.mmproj-f16.gguf b/MedGemma-GRPO.mmproj-f16.gguf new file mode 100644 index 0000000..db9be83 --- /dev/null +++ b/MedGemma-GRPO.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3c19bcf6ea8d968df3b3b967a2e2b360d24496cdcff180f9bacf3a3c0cb18ad +size 851251936 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4785991 --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: lastmass/MedGemma-GRPO +datasets: +- FreedomIntelligence/medical-o1-reasoning-SFT +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- gemma3 +- vllm +- MedGemma +--- +## About + + + + + + + + + +static quants of https://huggingface.co/lastmass/MedGemma-GRPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MedGemma-GRPO-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/MedGemma-GRPO-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/MedGemma-GRPO-GGUF/resolve/main/MedGemma-GRPO.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.7 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-GGUF/resolve/main/MedGemma-GRPO.mmproj-f16.gguf) | mmproj-f16 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-GGUF/resolve/main/MedGemma-GRPO.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-GGUF/resolve/main/MedGemma-GRPO.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-GGUF/resolve/main/MedGemma-GRPO.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-GGUF/resolve/main/MedGemma-GRPO.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-GGUF/resolve/main/MedGemma-GRPO.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-GGUF/resolve/main/MedGemma-GRPO.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-GGUF/resolve/main/MedGemma-GRPO.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-GGUF/resolve/main/MedGemma-GRPO.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-GGUF/resolve/main/MedGemma-GRPO.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-GGUF/resolve/main/MedGemma-GRPO.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-GGUF/resolve/main/MedGemma-GRPO.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-GGUF/resolve/main/MedGemma-GRPO.f16.gguf) | f16 | 7.9 | 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. + +