commit 48f7368c5eb11737637d304d7a0e88390b3ceeac Author: ModelHub XC Date: Thu Oct 15 14:04:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/overthinker_v0.5-qwen-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4b5e7e5 --- /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 +overthinker_v0.5-qwen.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +overthinker_v0.5-qwen.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +overthinker_v0.5-qwen.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +overthinker_v0.5-qwen.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +overthinker_v0.5-qwen.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +overthinker_v0.5-qwen.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +overthinker_v0.5-qwen.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +overthinker_v0.5-qwen.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +overthinker_v0.5-qwen.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +overthinker_v0.5-qwen.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +overthinker_v0.5-qwen.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +overthinker_v0.5-qwen.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..88a28fe --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: takenusername32/overthinker_v0.5-qwen +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/takenusername32/overthinker_v0.5-qwen + + +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/overthinker_v0.5-qwen-GGUF/resolve/main/overthinker_v0.5-qwen.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/overthinker_v0.5-qwen-GGUF/resolve/main/overthinker_v0.5-qwen.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/overthinker_v0.5-qwen-GGUF/resolve/main/overthinker_v0.5-qwen.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/overthinker_v0.5-qwen-GGUF/resolve/main/overthinker_v0.5-qwen.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/overthinker_v0.5-qwen-GGUF/resolve/main/overthinker_v0.5-qwen.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/overthinker_v0.5-qwen-GGUF/resolve/main/overthinker_v0.5-qwen.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/overthinker_v0.5-qwen-GGUF/resolve/main/overthinker_v0.5-qwen.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/overthinker_v0.5-qwen-GGUF/resolve/main/overthinker_v0.5-qwen.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/overthinker_v0.5-qwen-GGUF/resolve/main/overthinker_v0.5-qwen.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/overthinker_v0.5-qwen-GGUF/resolve/main/overthinker_v0.5-qwen.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/overthinker_v0.5-qwen-GGUF/resolve/main/overthinker_v0.5-qwen.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/overthinker_v0.5-qwen-GGUF/resolve/main/overthinker_v0.5-qwen.f16.gguf) | f16 | 3.2 | 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. + + diff --git a/overthinker_v0.5-qwen.IQ4_XS.gguf b/overthinker_v0.5-qwen.IQ4_XS.gguf new file mode 100644 index 0000000..f004393 --- /dev/null +++ b/overthinker_v0.5-qwen.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5ddaaf5ce223ee8fc9067a286416cfb5eeab663f174522c0f8355371617c7c6 +size 902182816 diff --git a/overthinker_v0.5-qwen.Q2_K.gguf b/overthinker_v0.5-qwen.Q2_K.gguf new file mode 100644 index 0000000..f607b39 --- /dev/null +++ b/overthinker_v0.5-qwen.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bfeb7b3980844811ffa1e664af44d35babc8ae14b89485c255238e80ee83615 +size 676304800 diff --git a/overthinker_v0.5-qwen.Q3_K_L.gguf b/overthinker_v0.5-qwen.Q3_K_L.gguf new file mode 100644 index 0000000..83d20eb --- /dev/null +++ b/overthinker_v0.5-qwen.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e37fbe03c1277fce2acb141eb60cc4ae7971ae698be376c64825bd645bd62c7 +size 880162720 diff --git a/overthinker_v0.5-qwen.Q3_K_M.gguf b/overthinker_v0.5-qwen.Q3_K_M.gguf new file mode 100644 index 0000000..f9e5845 --- /dev/null +++ b/overthinker_v0.5-qwen.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8f3efc2b880274cd8d57f63811ad07dfb84bd16e4d720d340c7c3274965fdbb +size 824178592 diff --git a/overthinker_v0.5-qwen.Q3_K_S.gguf b/overthinker_v0.5-qwen.Q3_K_S.gguf new file mode 100644 index 0000000..ac2d44b --- /dev/null +++ b/overthinker_v0.5-qwen.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e51034ed92bee45b1d39cac58299985470366feed20ccea832f67b6218dfe89 +size 760944544 diff --git a/overthinker_v0.5-qwen.Q4_K_M.gguf b/overthinker_v0.5-qwen.Q4_K_M.gguf new file mode 100644 index 0000000..309cce4 --- /dev/null +++ b/overthinker_v0.5-qwen.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ae1d4bb8f8773a7ce8d0d6160963c1d397671389e2d9f9ab7dc535142e81f2c +size 986048416 diff --git a/overthinker_v0.5-qwen.Q4_K_S.gguf b/overthinker_v0.5-qwen.Q4_K_S.gguf new file mode 100644 index 0000000..a5f8e3d --- /dev/null +++ b/overthinker_v0.5-qwen.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:692b08ea1b73799b63995db1414f21e7e1fc991891fcd17a017ea5c381fdb988 +size 940312480 diff --git a/overthinker_v0.5-qwen.Q5_K_M.gguf b/overthinker_v0.5-qwen.Q5_K_M.gguf new file mode 100644 index 0000000..8c2b3f3 --- /dev/null +++ b/overthinker_v0.5-qwen.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:662c24e013848a5ed1536098f2866ea03134869047f7535ee4e4c6f2d5aad4a0 +size 1125050272 diff --git a/overthinker_v0.5-qwen.Q5_K_S.gguf b/overthinker_v0.5-qwen.Q5_K_S.gguf new file mode 100644 index 0000000..256e76e --- /dev/null +++ b/overthinker_v0.5-qwen.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09901184662f7ee7a47de6bf17f00738960963778f0ad338f3daaf702bf6b261 +size 1098729376 diff --git a/overthinker_v0.5-qwen.Q6_K.gguf b/overthinker_v0.5-qwen.Q6_K.gguf new file mode 100644 index 0000000..ac8d728 --- /dev/null +++ b/overthinker_v0.5-qwen.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61985a818c5803ba6061105a060e5ea553f37e637945cc1d739fa08ba8f82061 +size 1272739744 diff --git a/overthinker_v0.5-qwen.Q8_0.gguf b/overthinker_v0.5-qwen.Q8_0.gguf new file mode 100644 index 0000000..9407907 --- /dev/null +++ b/overthinker_v0.5-qwen.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46747e93648e94cc6ca58284988a88cb7bd4dfca626d0500449dd6e4f44709b4 +size 1646572960 diff --git a/overthinker_v0.5-qwen.f16.gguf b/overthinker_v0.5-qwen.f16.gguf new file mode 100644 index 0000000..ee89122 --- /dev/null +++ b/overthinker_v0.5-qwen.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41801ffbe9b3c44a9a0a28737f746116f31a6801625d37b9aaf17e2240c1eb66 +size 3093669280