commit 4a464c0fa8a40271e5e18e608212199844a675eb Author: ModelHub XC Date: Sun Jun 21 01:02:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AlRazi0.1-Medical-Thinking-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d1a3d72 --- /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 +AlRazi0.1-Medical-Thinking.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +AlRazi0.1-Medical-Thinking.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AlRazi0.1-Medical-Thinking.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AlRazi0.1-Medical-Thinking.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AlRazi0.1-Medical-Thinking.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AlRazi0.1-Medical-Thinking.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AlRazi0.1-Medical-Thinking.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AlRazi0.1-Medical-Thinking.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AlRazi0.1-Medical-Thinking.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AlRazi0.1-Medical-Thinking.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AlRazi0.1-Medical-Thinking.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AlRazi0.1-Medical-Thinking.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AlRazi0.1-Medical-Thinking.IQ4_XS.gguf b/AlRazi0.1-Medical-Thinking.IQ4_XS.gguf new file mode 100644 index 0000000..2374139 --- /dev/null +++ b/AlRazi0.1-Medical-Thinking.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d469a5e2cf63c507b66e0f2ca18bf459f763f2116715e3c42d5e81e622b52d4 +size 1840906944 diff --git a/AlRazi0.1-Medical-Thinking.Q2_K.gguf b/AlRazi0.1-Medical-Thinking.Q2_K.gguf new file mode 100644 index 0000000..54fa4ce --- /dev/null +++ b/AlRazi0.1-Medical-Thinking.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c5f1d12a068658c7ec06b8d9bf48a8ba818b1685b8dfdb554b8aeca585f08f6 +size 1363935936 diff --git a/AlRazi0.1-Medical-Thinking.Q3_K_L.gguf b/AlRazi0.1-Medical-Thinking.Q3_K_L.gguf new file mode 100644 index 0000000..5e0dfec --- /dev/null +++ b/AlRazi0.1-Medical-Thinking.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7d01e6a670a9e29e88d0c3d4018049018eabc1a26751e271a0cdf408aea35c9 +size 1815347904 diff --git a/AlRazi0.1-Medical-Thinking.Q3_K_M.gguf b/AlRazi0.1-Medical-Thinking.Q3_K_M.gguf new file mode 100644 index 0000000..d55cf04 --- /dev/null +++ b/AlRazi0.1-Medical-Thinking.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14f3a16c4a8d4907d0150cdaa318c4150bce91baaa574021488db83f8b7fcd3d +size 1687159488 diff --git a/AlRazi0.1-Medical-Thinking.Q3_K_S.gguf b/AlRazi0.1-Medical-Thinking.Q3_K_S.gguf new file mode 100644 index 0000000..ba26311 --- /dev/null +++ b/AlRazi0.1-Medical-Thinking.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c73ebc44dc3ffb01f1d93c057633c146a8e9d1d74326d9e2ed8d6471d679a43d +size 1542849216 diff --git a/AlRazi0.1-Medical-Thinking.Q4_K_M.gguf b/AlRazi0.1-Medical-Thinking.Q4_K_M.gguf new file mode 100644 index 0000000..af4e0a9 --- /dev/null +++ b/AlRazi0.1-Medical-Thinking.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6576d45e27700363d7aa5b67311f6e0232adaefff0a0ada4461f7f3ff716fd1 +size 2019377856 diff --git a/AlRazi0.1-Medical-Thinking.Q4_K_S.gguf b/AlRazi0.1-Medical-Thinking.Q4_K_S.gguf new file mode 100644 index 0000000..685f425 --- /dev/null +++ b/AlRazi0.1-Medical-Thinking.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba91c733c86e77b3714086b4d9ed7d9172c1fd821476f49f5a839edb4e7a00f5 +size 1928200896 diff --git a/AlRazi0.1-Medical-Thinking.Q5_K_M.gguf b/AlRazi0.1-Medical-Thinking.Q5_K_M.gguf new file mode 100644 index 0000000..4b0ea16 --- /dev/null +++ b/AlRazi0.1-Medical-Thinking.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f9d61a331e22dcdc979db2b80d330df35c7ef23c1832306e34d39116ed943fc +size 2322154176 diff --git a/AlRazi0.1-Medical-Thinking.Q5_K_S.gguf b/AlRazi0.1-Medical-Thinking.Q5_K_S.gguf new file mode 100644 index 0000000..971fb1e --- /dev/null +++ b/AlRazi0.1-Medical-Thinking.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f06e294764e5b678fcbec28780772b2975e818b8074fe2f6bc430cb9a6081bf6 +size 2269512384 diff --git a/AlRazi0.1-Medical-Thinking.Q6_K.gguf b/AlRazi0.1-Medical-Thinking.Q6_K.gguf new file mode 100644 index 0000000..e000a2d --- /dev/null +++ b/AlRazi0.1-Medical-Thinking.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4974f49a8bc0c55486c5c691b0487ad238e658ec1dc154390fe3c7989bed6c8f +size 2643854016 diff --git a/AlRazi0.1-Medical-Thinking.Q8_0.gguf b/AlRazi0.1-Medical-Thinking.Q8_0.gguf new file mode 100644 index 0000000..2d5f1b7 --- /dev/null +++ b/AlRazi0.1-Medical-Thinking.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52be3585e571a49fb8cf0a1b8f3663cf4a66cf1cfa3577f7a4aac5bdd865e8f4 +size 3421899456 diff --git a/AlRazi0.1-Medical-Thinking.f16.gguf b/AlRazi0.1-Medical-Thinking.f16.gguf new file mode 100644 index 0000000..02779ff --- /dev/null +++ b/AlRazi0.1-Medical-Thinking.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:128e6d5b97212214c21c43733ee65c8c7fd6bf6258f2d29cca432c47fb483c97 +size 6433688256 diff --git a/README.md b/README.md new file mode 100644 index 0000000..99daffd --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: OussamaEL/AlRazi0.1-Medical-Thinking +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- unsloth +- trl +- grpo +--- +## About + + + + + + +static quants of https://huggingface.co/OussamaEL/AlRazi0.1-Medical-Thinking + + +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/AlRazi0.1-Medical-Thinking-GGUF/resolve/main/AlRazi0.1-Medical-Thinking.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/AlRazi0.1-Medical-Thinking-GGUF/resolve/main/AlRazi0.1-Medical-Thinking.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/AlRazi0.1-Medical-Thinking-GGUF/resolve/main/AlRazi0.1-Medical-Thinking.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AlRazi0.1-Medical-Thinking-GGUF/resolve/main/AlRazi0.1-Medical-Thinking.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/AlRazi0.1-Medical-Thinking-GGUF/resolve/main/AlRazi0.1-Medical-Thinking.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/AlRazi0.1-Medical-Thinking-GGUF/resolve/main/AlRazi0.1-Medical-Thinking.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AlRazi0.1-Medical-Thinking-GGUF/resolve/main/AlRazi0.1-Medical-Thinking.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AlRazi0.1-Medical-Thinking-GGUF/resolve/main/AlRazi0.1-Medical-Thinking.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/AlRazi0.1-Medical-Thinking-GGUF/resolve/main/AlRazi0.1-Medical-Thinking.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/AlRazi0.1-Medical-Thinking-GGUF/resolve/main/AlRazi0.1-Medical-Thinking.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/AlRazi0.1-Medical-Thinking-GGUF/resolve/main/AlRazi0.1-Medical-Thinking.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/AlRazi0.1-Medical-Thinking-GGUF/resolve/main/AlRazi0.1-Medical-Thinking.f16.gguf) | f16 | 6.5 | 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. + +