commit ed0ec59ce080efd3f463f26347bc22920f20eee2 Author: ModelHub XC Date: Tue May 12 00:56:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/KnowMedPhi3.5-mini-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f0ac91b --- /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 +KnowMedPhi3.5-mini.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +KnowMedPhi3.5-mini.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KnowMedPhi3.5-mini.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KnowMedPhi3.5-mini.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KnowMedPhi3.5-mini.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KnowMedPhi3.5-mini.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KnowMedPhi3.5-mini.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KnowMedPhi3.5-mini.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KnowMedPhi3.5-mini.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KnowMedPhi3.5-mini.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KnowMedPhi3.5-mini.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +KnowMedPhi3.5-mini.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KnowMedPhi3.5-mini.IQ4_XS.gguf b/KnowMedPhi3.5-mini.IQ4_XS.gguf new file mode 100644 index 0000000..404d05f --- /dev/null +++ b/KnowMedPhi3.5-mini.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f54ad588f4e1ebdbe17a1d0778576a36156e447c495a3aba1d9ac06b3aee3e8d +size 2075581088 diff --git a/KnowMedPhi3.5-mini.Q2_K.gguf b/KnowMedPhi3.5-mini.Q2_K.gguf new file mode 100644 index 0000000..c4342d2 --- /dev/null +++ b/KnowMedPhi3.5-mini.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78c8ea0637c28ddf32f725f901b38e713dfb50b823b8efc6971610a8d4bbc06a +size 1508216480 diff --git a/KnowMedPhi3.5-mini.Q3_K_L.gguf b/KnowMedPhi3.5-mini.Q3_K_L.gguf new file mode 100644 index 0000000..41c64fc --- /dev/null +++ b/KnowMedPhi3.5-mini.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb79d11ce25ea0a6890ffdb157e8fbbdfc9766514cc779059c896bfc91754b87 +size 2200843424 diff --git a/KnowMedPhi3.5-mini.Q3_K_M.gguf b/KnowMedPhi3.5-mini.Q3_K_M.gguf new file mode 100644 index 0000000..c30f4e4 --- /dev/null +++ b/KnowMedPhi3.5-mini.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20c2564cff7d9aa7c01b785b8fbdb54af0cf3de53446d10016c37d38215bb41d +size 1962554528 diff --git a/KnowMedPhi3.5-mini.Q3_K_S.gguf b/KnowMedPhi3.5-mini.Q3_K_S.gguf new file mode 100644 index 0000000..f850088 --- /dev/null +++ b/KnowMedPhi3.5-mini.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9ec4f1d28a48f52e5430f8b89144f641ad40d435030c4e3668600af33d1883a +size 1681798304 diff --git a/KnowMedPhi3.5-mini.Q4_K_M.gguf b/KnowMedPhi3.5-mini.Q4_K_M.gguf new file mode 100644 index 0000000..9a028c4 --- /dev/null +++ b/KnowMedPhi3.5-mini.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31ace63a450a1dabb68d68153a68daff62466d41de5c2dcdde896687a752d1f4 +size 2396770976 diff --git a/KnowMedPhi3.5-mini.Q4_K_S.gguf b/KnowMedPhi3.5-mini.Q4_K_S.gguf new file mode 100644 index 0000000..b139d27 --- /dev/null +++ b/KnowMedPhi3.5-mini.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbaa21f916ca4dad6d9858b859d01e94295078e954e39c90bd1a77fa262a77e9 +size 2202915488 diff --git a/KnowMedPhi3.5-mini.Q5_K_M.gguf b/KnowMedPhi3.5-mini.Q5_K_M.gguf new file mode 100644 index 0000000..e86670f --- /dev/null +++ b/KnowMedPhi3.5-mini.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07961cf844005c3bb09e9c8908e0b344dd504ab0316ec4ff2161c76765dd26a7 +size 2755113632 diff --git a/KnowMedPhi3.5-mini.Q5_K_S.gguf b/KnowMedPhi3.5-mini.Q5_K_S.gguf new file mode 100644 index 0000000..b0a9dfa --- /dev/null +++ b/KnowMedPhi3.5-mini.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c4c0c703c27e189eee25287d4ff0bb2d91a65aa481bfacb990c112d7423ec38 +size 2641474208 diff --git a/KnowMedPhi3.5-mini.Q6_K.gguf b/KnowMedPhi3.5-mini.Q6_K.gguf new file mode 100644 index 0000000..4bb3b4f --- /dev/null +++ b/KnowMedPhi3.5-mini.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c8bb9305bada8fe6d2473e7f835a853f200e9d5d44196dbfcca1a5c04bfc29f +size 3135852704 diff --git a/KnowMedPhi3.5-mini.Q8_0.gguf b/KnowMedPhi3.5-mini.Q8_0.gguf new file mode 100644 index 0000000..851205e --- /dev/null +++ b/KnowMedPhi3.5-mini.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8cb4ede2457cf6388b0af59bc085e1e464e1276e63c52d327fb3e18b5595509 +size 4061222048 diff --git a/KnowMedPhi3.5-mini.f16.gguf b/KnowMedPhi3.5-mini.f16.gguf new file mode 100644 index 0000000..6c6c66a --- /dev/null +++ b/KnowMedPhi3.5-mini.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:210649e1605a040d57b5d4abc414fe6100edd44767f18ecf42b97d8ff59a4a0f +size 7643296928 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a7efe98 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: knowlab-research/KnowMedPhi3.5-mini +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/knowlab-research/KnowMedPhi3.5-mini + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#KnowMedPhi3.5-mini-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/KnowMedPhi3.5-mini-GGUF/resolve/main/KnowMedPhi3.5-mini.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/KnowMedPhi3.5-mini-GGUF/resolve/main/KnowMedPhi3.5-mini.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/KnowMedPhi3.5-mini-GGUF/resolve/main/KnowMedPhi3.5-mini.Q3_K_M.gguf) | Q3_K_M | 2.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KnowMedPhi3.5-mini-GGUF/resolve/main/KnowMedPhi3.5-mini.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/KnowMedPhi3.5-mini-GGUF/resolve/main/KnowMedPhi3.5-mini.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/KnowMedPhi3.5-mini-GGUF/resolve/main/KnowMedPhi3.5-mini.Q4_K_S.gguf) | Q4_K_S | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KnowMedPhi3.5-mini-GGUF/resolve/main/KnowMedPhi3.5-mini.Q4_K_M.gguf) | Q4_K_M | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KnowMedPhi3.5-mini-GGUF/resolve/main/KnowMedPhi3.5-mini.Q5_K_S.gguf) | Q5_K_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/KnowMedPhi3.5-mini-GGUF/resolve/main/KnowMedPhi3.5-mini.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/KnowMedPhi3.5-mini-GGUF/resolve/main/KnowMedPhi3.5-mini.Q6_K.gguf) | Q6_K | 3.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/KnowMedPhi3.5-mini-GGUF/resolve/main/KnowMedPhi3.5-mini.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/KnowMedPhi3.5-mini-GGUF/resolve/main/KnowMedPhi3.5-mini.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. + +