commit ed0c60b223153db515c9dcafd7f6b6a54fad8eff Author: ModelHub XC Date: Wed Oct 14 02:36:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MedQwen3-8B-SFT-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b4878f6 --- /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 +MedQwen3-8B-SFT-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text +MedQwen3-8B-SFT-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedQwen3-8B-SFT-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MedQwen3-8B-SFT-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MedQwen3-8B-SFT-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MedQwen3-8B-SFT-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedQwen3-8B-SFT-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedQwen3-8B-SFT-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MedQwen3-8B-SFT-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedQwen3-8B-SFT-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedQwen3-8B-SFT-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedQwen3-8B-SFT-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MedQwen3-8B-SFT-v2.IQ4_XS.gguf b/MedQwen3-8B-SFT-v2.IQ4_XS.gguf new file mode 100644 index 0000000..a5f0fe8 --- /dev/null +++ b/MedQwen3-8B-SFT-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaa3e1da9c69c7ca6c5bca0b7a0dee56e3edbd65d67f9f63d9db70096758d5ac +size 4593298048 diff --git a/MedQwen3-8B-SFT-v2.Q2_K.gguf b/MedQwen3-8B-SFT-v2.Q2_K.gguf new file mode 100644 index 0000000..2df712f --- /dev/null +++ b/MedQwen3-8B-SFT-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:433c6b3ee726a6f4529d3739f4bb53433dd6ad62d537f98335699da2825fc224 +size 3281734272 diff --git a/MedQwen3-8B-SFT-v2.Q3_K_L.gguf b/MedQwen3-8B-SFT-v2.Q3_K_L.gguf new file mode 100644 index 0000000..a3cc680 --- /dev/null +++ b/MedQwen3-8B-SFT-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe5c2b4d8284ad0e2603ba82c1f86270c7259496ea5628eb49265bfcb49b3ed0 +size 4431395456 diff --git a/MedQwen3-8B-SFT-v2.Q3_K_M.gguf b/MedQwen3-8B-SFT-v2.Q3_K_M.gguf new file mode 100644 index 0000000..e48d009 --- /dev/null +++ b/MedQwen3-8B-SFT-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:264cc62aea0a6494ef10b94d7484015f484f7803fb582f2e7e834b09f1d5f4a4 +size 4124162688 diff --git a/MedQwen3-8B-SFT-v2.Q3_K_S.gguf b/MedQwen3-8B-SFT-v2.Q3_K_S.gguf new file mode 100644 index 0000000..4de055a --- /dev/null +++ b/MedQwen3-8B-SFT-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b1c937e555122dc4385e1054aaf920d8ea610648d2dce68031131988c1e4cde +size 3769612928 diff --git a/MedQwen3-8B-SFT-v2.Q4_K_M.gguf b/MedQwen3-8B-SFT-v2.Q4_K_M.gguf new file mode 100644 index 0000000..c74842c --- /dev/null +++ b/MedQwen3-8B-SFT-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df9a6eaeadcbdc22ded8f5e2634e6f81e343f95c625558135e45916ab080b58d +size 5027785344 diff --git a/MedQwen3-8B-SFT-v2.Q4_K_S.gguf b/MedQwen3-8B-SFT-v2.Q4_K_S.gguf new file mode 100644 index 0000000..a76b785 --- /dev/null +++ b/MedQwen3-8B-SFT-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:772c80d4b9367aff02292841cd31ffc82ea308e14f81383ac9f88d431bda9100 +size 4802013824 diff --git a/MedQwen3-8B-SFT-v2.Q5_K_M.gguf b/MedQwen3-8B-SFT-v2.Q5_K_M.gguf new file mode 100644 index 0000000..f2e0af8 --- /dev/null +++ b/MedQwen3-8B-SFT-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ae485a26707717b94c3f436b29bfe7690cb00698c7e844068f327bd6f7478dd +size 5851114112 diff --git a/MedQwen3-8B-SFT-v2.Q5_K_S.gguf b/MedQwen3-8B-SFT-v2.Q5_K_S.gguf new file mode 100644 index 0000000..41a2099 --- /dev/null +++ b/MedQwen3-8B-SFT-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56511105e2d6c885f216dd097ee7f716d34874891b5319185adab43ea935da10 +size 5720763008 diff --git a/MedQwen3-8B-SFT-v2.Q6_K.gguf b/MedQwen3-8B-SFT-v2.Q6_K.gguf new file mode 100644 index 0000000..851dbc8 --- /dev/null +++ b/MedQwen3-8B-SFT-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88d373e590514e93734b153669a160fc7267eb56bf8ca3a610c41d10340867b9 +size 6725900928 diff --git a/MedQwen3-8B-SFT-v2.Q8_0.gguf b/MedQwen3-8B-SFT-v2.Q8_0.gguf new file mode 100644 index 0000000..fb848eb --- /dev/null +++ b/MedQwen3-8B-SFT-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c9c6c706277a20fbb4cc3a27e97889dcb28a48b44d8ad012a15530ff14e3538 +size 8709520000 diff --git a/MedQwen3-8B-SFT-v2.f16.gguf b/MedQwen3-8B-SFT-v2.f16.gguf new file mode 100644 index 0000000..80a7b5f --- /dev/null +++ b/MedQwen3-8B-SFT-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fcf236f6fe1085fc113f82ff39f88431cca80dd8ab7efd3829356688e7b87d3 +size 16388045440 diff --git a/README.md b/README.md new file mode 100644 index 0000000..69fb9bd --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: zypchn/MedQwen3-8B-SFT-v2 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/zypchn/MedQwen3-8B-SFT-v2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MedQwen3-8B-SFT-v2-GGUF).*** + +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/MedQwen3-8B-SFT-v2-GGUF/resolve/main/MedQwen3-8B-SFT-v2.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/MedQwen3-8B-SFT-v2-GGUF/resolve/main/MedQwen3-8B-SFT-v2.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MedQwen3-8B-SFT-v2-GGUF/resolve/main/MedQwen3-8B-SFT-v2.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MedQwen3-8B-SFT-v2-GGUF/resolve/main/MedQwen3-8B-SFT-v2.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/MedQwen3-8B-SFT-v2-GGUF/resolve/main/MedQwen3-8B-SFT-v2.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/MedQwen3-8B-SFT-v2-GGUF/resolve/main/MedQwen3-8B-SFT-v2.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MedQwen3-8B-SFT-v2-GGUF/resolve/main/MedQwen3-8B-SFT-v2.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MedQwen3-8B-SFT-v2-GGUF/resolve/main/MedQwen3-8B-SFT-v2.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/MedQwen3-8B-SFT-v2-GGUF/resolve/main/MedQwen3-8B-SFT-v2.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/MedQwen3-8B-SFT-v2-GGUF/resolve/main/MedQwen3-8B-SFT-v2.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MedQwen3-8B-SFT-v2-GGUF/resolve/main/MedQwen3-8B-SFT-v2.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MedQwen3-8B-SFT-v2-GGUF/resolve/main/MedQwen3-8B-SFT-v2.f16.gguf) | f16 | 16.5 | 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. + +