commit 7d2f1d48d4e8e852ce72903835264a5ae19495ae Author: ModelHub XC Date: Mon Apr 13 13:25:03 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Q2.5-Qwetiapin-32B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f2b9ef7 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +Q2.5-Qwetiapin-32B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Q2.5-Qwetiapin-32B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Q2.5-Qwetiapin-32B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Q2.5-Qwetiapin-32B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Q2.5-Qwetiapin-32B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Q2.5-Qwetiapin-32B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Q2.5-Qwetiapin-32B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Q2.5-Qwetiapin-32B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Q2.5-Qwetiapin-32B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Q2.5-Qwetiapin-32B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Q2.5-Qwetiapin-32B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Q2.5-Qwetiapin-32B.IQ4_XS.gguf b/Q2.5-Qwetiapin-32B.IQ4_XS.gguf new file mode 100644 index 0000000..1dc8dbf --- /dev/null +++ b/Q2.5-Qwetiapin-32B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb70db6131ea2bffa13e1b3994a3eb14fc3981d2f0098e7a90bcfe6f65becf7e +size 17867331744 diff --git a/Q2.5-Qwetiapin-32B.Q2_K.gguf b/Q2.5-Qwetiapin-32B.Q2_K.gguf new file mode 100644 index 0000000..c5bdf1a --- /dev/null +++ b/Q2.5-Qwetiapin-32B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9611463c0876c37bec422d25906a8735f8fc11c79fdf01f9923e9a1637cfc90 +size 12310744480 diff --git a/Q2.5-Qwetiapin-32B.Q3_K_L.gguf b/Q2.5-Qwetiapin-32B.Q3_K_L.gguf new file mode 100644 index 0000000..54fd4bd --- /dev/null +++ b/Q2.5-Qwetiapin-32B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa36709feae6c363ea25e46fedddb37f7fb5c2de892c6dcc395b40b65e50d982 +size 17244517152 diff --git a/Q2.5-Qwetiapin-32B.Q3_K_M.gguf b/Q2.5-Qwetiapin-32B.Q3_K_M.gguf new file mode 100644 index 0000000..3ed1caf --- /dev/null +++ b/Q2.5-Qwetiapin-32B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8669ed1b886149e8dfdd7f129796bd7dd9c357558fd103f4da99cf98471807ad +size 15932486432 diff --git a/Q2.5-Qwetiapin-32B.Q3_K_S.gguf b/Q2.5-Qwetiapin-32B.Q3_K_S.gguf new file mode 100644 index 0000000..a7cdbf6 --- /dev/null +++ b/Q2.5-Qwetiapin-32B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5575dd073728d4364ab6dd710673e6176f33c13ac6555632bcefd09418dfbad1 +size 14389768992 diff --git a/Q2.5-Qwetiapin-32B.Q4_K_M.gguf b/Q2.5-Qwetiapin-32B.Q4_K_M.gguf new file mode 100644 index 0000000..b568141 --- /dev/null +++ b/Q2.5-Qwetiapin-32B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a068411088e9fdcc0c7e26bbf5fd84237f8994668164ddc2924ff6b4ca1b2128 +size 19848503104 diff --git a/Q2.5-Qwetiapin-32B.Q4_K_S.gguf b/Q2.5-Qwetiapin-32B.Q4_K_S.gguf new file mode 100644 index 0000000..a0ed82e --- /dev/null +++ b/Q2.5-Qwetiapin-32B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e20bf6252a19dfee255caae5105544f06b1bcae0affd91ee3698a04204ac32f +size 18781577024 diff --git a/Q2.5-Qwetiapin-32B.Q5_K_M.gguf b/Q2.5-Qwetiapin-32B.Q5_K_M.gguf new file mode 100644 index 0000000..5adc730 --- /dev/null +++ b/Q2.5-Qwetiapin-32B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6225c4b13c887ba5c64b2b7082b7c71d7d7593a6144e5c72bdff0ef140d6506 +size 23259068864 diff --git a/Q2.5-Qwetiapin-32B.Q5_K_S.gguf b/Q2.5-Qwetiapin-32B.Q5_K_S.gguf new file mode 100644 index 0000000..e75901e --- /dev/null +++ b/Q2.5-Qwetiapin-32B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:189cc279dc1ccd5e55eec81cc9fb40875b919c870016ff4082eeaa4b6e62f2cd +size 22635166144 diff --git a/Q2.5-Qwetiapin-32B.Q6_K.gguf b/Q2.5-Qwetiapin-32B.Q6_K.gguf new file mode 100644 index 0000000..866486e --- /dev/null +++ b/Q2.5-Qwetiapin-32B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de20220f81a438a02803602ec59a5c3e17766aa71fb0ea57d230c3dc8be3c256 +size 26882795008 diff --git a/Q2.5-Qwetiapin-32B.Q8_0.gguf b/Q2.5-Qwetiapin-32B.Q8_0.gguf new file mode 100644 index 0000000..852956c --- /dev/null +++ b/Q2.5-Qwetiapin-32B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dabe0fd967a572ded0775b490424f570c5f3c3576dbdebb257f1a1b0f543425a +size 34816535680 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8c08905 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: Nohobby/Q2.5-Qwetiapin-32B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Nohobby/Q2.5-Qwetiapin-32B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Q2.5-Qwetiapin-32B-i1-GGUF +## 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/Q2.5-Qwetiapin-32B-GGUF/resolve/main/Q2.5-Qwetiapin-32B.Q2_K.gguf) | Q2_K | 12.4 | | +| [GGUF](https://huggingface.co/mradermacher/Q2.5-Qwetiapin-32B-GGUF/resolve/main/Q2.5-Qwetiapin-32B.Q3_K_S.gguf) | Q3_K_S | 14.5 | | +| [GGUF](https://huggingface.co/mradermacher/Q2.5-Qwetiapin-32B-GGUF/resolve/main/Q2.5-Qwetiapin-32B.Q3_K_M.gguf) | Q3_K_M | 16.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Q2.5-Qwetiapin-32B-GGUF/resolve/main/Q2.5-Qwetiapin-32B.Q3_K_L.gguf) | Q3_K_L | 17.3 | | +| [GGUF](https://huggingface.co/mradermacher/Q2.5-Qwetiapin-32B-GGUF/resolve/main/Q2.5-Qwetiapin-32B.IQ4_XS.gguf) | IQ4_XS | 18.0 | | +| [GGUF](https://huggingface.co/mradermacher/Q2.5-Qwetiapin-32B-GGUF/resolve/main/Q2.5-Qwetiapin-32B.Q4_K_S.gguf) | Q4_K_S | 18.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Q2.5-Qwetiapin-32B-GGUF/resolve/main/Q2.5-Qwetiapin-32B.Q4_K_M.gguf) | Q4_K_M | 19.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Q2.5-Qwetiapin-32B-GGUF/resolve/main/Q2.5-Qwetiapin-32B.Q5_K_S.gguf) | Q5_K_S | 22.7 | | +| [GGUF](https://huggingface.co/mradermacher/Q2.5-Qwetiapin-32B-GGUF/resolve/main/Q2.5-Qwetiapin-32B.Q5_K_M.gguf) | Q5_K_M | 23.4 | | +| [GGUF](https://huggingface.co/mradermacher/Q2.5-Qwetiapin-32B-GGUF/resolve/main/Q2.5-Qwetiapin-32B.Q6_K.gguf) | Q6_K | 27.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Q2.5-Qwetiapin-32B-GGUF/resolve/main/Q2.5-Qwetiapin-32B.Q8_0.gguf) | Q8_0 | 34.9 | fast, best quality | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +