commit 2176b76a0495c62e56b8d24d5b3685fa06d80061 Author: ModelHub XC Date: Mon Jun 15 00:22:20 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/MedSummary-Qwen3-0.6B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d6ffc72 --- /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 +MedSummary-Qwen3-0.6B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MedSummary-Qwen3-0.6B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MedSummary-Qwen3-0.6B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MedSummary-Qwen3-0.6B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedSummary-Qwen3-0.6B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedSummary-Qwen3-0.6B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedSummary-Qwen3-0.6B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedSummary-Qwen3-0.6B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedSummary-Qwen3-0.6B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedSummary-Qwen3-0.6B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MedSummary-Qwen3-0.6B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MedSummary-Qwen3-0.6B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MedSummary-Qwen3-0.6B.IQ4_XS.gguf b/MedSummary-Qwen3-0.6B.IQ4_XS.gguf new file mode 100644 index 0000000..d3532c9 --- /dev/null +++ b/MedSummary-Qwen3-0.6B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d28eda3756bb75d0e77e3795cc860a88615ae4b5eca47b162e543332fb3aa7e6 +size 369278080 diff --git a/MedSummary-Qwen3-0.6B.Q2_K.gguf b/MedSummary-Qwen3-0.6B.Q2_K.gguf new file mode 100644 index 0000000..fd782fb --- /dev/null +++ b/MedSummary-Qwen3-0.6B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71036f6785f3532c58e5136a3cbadbf42e9f5b8ac1c94afb3e6ab969b7a3e38d +size 296238208 diff --git a/MedSummary-Qwen3-0.6B.Q3_K_L.gguf b/MedSummary-Qwen3-0.6B.Q3_K_L.gguf new file mode 100644 index 0000000..1399b1d --- /dev/null +++ b/MedSummary-Qwen3-0.6B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8daf73e3865e6d17ec5ccebb10b2f90fd1a2ba6dd5fbc17df168fc6a45ff80c8 +size 368491648 diff --git a/MedSummary-Qwen3-0.6B.Q3_K_M.gguf b/MedSummary-Qwen3-0.6B.Q3_K_M.gguf new file mode 100644 index 0000000..3315b97 --- /dev/null +++ b/MedSummary-Qwen3-0.6B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:823ac1a206ab75e82193df1304dfd16604a2f0d161d79155ed2a0c2c5e5dee6d +size 347126912 diff --git a/MedSummary-Qwen3-0.6B.Q3_K_S.gguf b/MedSummary-Qwen3-0.6B.Q3_K_S.gguf new file mode 100644 index 0000000..1d78a69 --- /dev/null +++ b/MedSummary-Qwen3-0.6B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70de940828965505e8b7992ebcc757261a31c98cfd8d7d57e45537672a145881 +size 323075200 diff --git a/MedSummary-Qwen3-0.6B.Q4_K_M.gguf b/MedSummary-Qwen3-0.6B.Q4_K_M.gguf new file mode 100644 index 0000000..6a46911 --- /dev/null +++ b/MedSummary-Qwen3-0.6B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de043ed91c2b4bb47415a762eb89a51ad4b0b032275a5e914c44562ec27f65d0 +size 396704896 diff --git a/MedSummary-Qwen3-0.6B.Q4_K_S.gguf b/MedSummary-Qwen3-0.6B.Q4_K_S.gguf new file mode 100644 index 0000000..80d703e --- /dev/null +++ b/MedSummary-Qwen3-0.6B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2753c8a797ad1bdb8192f36b3dbbad494a9104977bb2bb7b3d86b2da2a43ca7f +size 383270016 diff --git a/MedSummary-Qwen3-0.6B.Q5_K_M.gguf b/MedSummary-Qwen3-0.6B.Q5_K_M.gguf new file mode 100644 index 0000000..0fb7306 --- /dev/null +++ b/MedSummary-Qwen3-0.6B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:178ed95729cb6dcd7bb8d2fa80140c9b0f03bb927fad71b09c2a41ef969664e1 +size 444415104 diff --git a/MedSummary-Qwen3-0.6B.Q5_K_S.gguf b/MedSummary-Qwen3-0.6B.Q5_K_S.gguf new file mode 100644 index 0000000..2575b70 --- /dev/null +++ b/MedSummary-Qwen3-0.6B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dcd27be6cc55cefc9c87cb93f1cb8293770f52751bd11e360ab79326846ea60 +size 436616320 diff --git a/MedSummary-Qwen3-0.6B.Q6_K.gguf b/MedSummary-Qwen3-0.6B.Q6_K.gguf new file mode 100644 index 0000000..2609518 --- /dev/null +++ b/MedSummary-Qwen3-0.6B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:301f063ab99a503baaf0dccefb98d016fd753f1744af5aa7720c368612041409 +size 495107200 diff --git a/MedSummary-Qwen3-0.6B.Q8_0.gguf b/MedSummary-Qwen3-0.6B.Q8_0.gguf new file mode 100644 index 0000000..ccd0863 --- /dev/null +++ b/MedSummary-Qwen3-0.6B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f34e36d872b23c37295770c5867e6b296c063174714710f55a20846707b58186 +size 639447168 diff --git a/MedSummary-Qwen3-0.6B.f16.gguf b/MedSummary-Qwen3-0.6B.f16.gguf new file mode 100644 index 0000000..a42e7ac --- /dev/null +++ b/MedSummary-Qwen3-0.6B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f82edaa1d09dff1bece7181467b21b0d060041d0400777fa3b4d3f30eadfeb7b +size 1198182528 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0382445 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: singhprabhat/MedSummary-Qwen3-0.6B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/singhprabhat/MedSummary-Qwen3-0.6B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MedSummary-Qwen3-0.6B-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/MedSummary-Qwen3-0.6B-GGUF/resolve/main/MedSummary-Qwen3-0.6B.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/MedSummary-Qwen3-0.6B-GGUF/resolve/main/MedSummary-Qwen3-0.6B.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/MedSummary-Qwen3-0.6B-GGUF/resolve/main/MedSummary-Qwen3-0.6B.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MedSummary-Qwen3-0.6B-GGUF/resolve/main/MedSummary-Qwen3-0.6B.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/MedSummary-Qwen3-0.6B-GGUF/resolve/main/MedSummary-Qwen3-0.6B.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/MedSummary-Qwen3-0.6B-GGUF/resolve/main/MedSummary-Qwen3-0.6B.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MedSummary-Qwen3-0.6B-GGUF/resolve/main/MedSummary-Qwen3-0.6B.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MedSummary-Qwen3-0.6B-GGUF/resolve/main/MedSummary-Qwen3-0.6B.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/MedSummary-Qwen3-0.6B-GGUF/resolve/main/MedSummary-Qwen3-0.6B.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/MedSummary-Qwen3-0.6B-GGUF/resolve/main/MedSummary-Qwen3-0.6B.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MedSummary-Qwen3-0.6B-GGUF/resolve/main/MedSummary-Qwen3-0.6B.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MedSummary-Qwen3-0.6B-GGUF/resolve/main/MedSummary-Qwen3-0.6B.f16.gguf) | f16 | 1.3 | 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. + +