commit a70d638f0624829212320d91b6dccebeb734ac99 Author: ModelHub XC Date: Tue Apr 21 06:03:57 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Wise-Qwen-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ecf87f5 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +Wise-Qwen.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Wise-Qwen.f16.gguf filter=lfs diff=lfs merge=lfs -text +Wise-Qwen.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Wise-Qwen.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Wise-Qwen.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Wise-Qwen.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Wise-Qwen.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Wise-Qwen.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Wise-Qwen.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Wise-Qwen.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Wise-Qwen.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Wise-Qwen.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Wise-Qwen.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Wise-Qwen.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Wise-Qwen.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4806428 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: Abhaykoul/Wise-Qwen +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/Abhaykoul/Wise-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/Wise-Qwen-GGUF/resolve/main/Wise-Qwen.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Wise-Qwen-GGUF/resolve/main/Wise-Qwen.IQ3_XS.gguf) | IQ3_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Wise-Qwen-GGUF/resolve/main/Wise-Qwen.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Wise-Qwen-GGUF/resolve/main/Wise-Qwen.IQ3_S.gguf) | IQ3_S | 0.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Wise-Qwen-GGUF/resolve/main/Wise-Qwen.IQ3_M.gguf) | IQ3_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Wise-Qwen-GGUF/resolve/main/Wise-Qwen.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Wise-Qwen-GGUF/resolve/main/Wise-Qwen.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Wise-Qwen-GGUF/resolve/main/Wise-Qwen.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Wise-Qwen-GGUF/resolve/main/Wise-Qwen.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Wise-Qwen-GGUF/resolve/main/Wise-Qwen.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Wise-Qwen-GGUF/resolve/main/Wise-Qwen.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Wise-Qwen-GGUF/resolve/main/Wise-Qwen.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Wise-Qwen-GGUF/resolve/main/Wise-Qwen.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Wise-Qwen-GGUF/resolve/main/Wise-Qwen.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Wise-Qwen-GGUF/resolve/main/Wise-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/Wise-Qwen.IQ3_M.gguf b/Wise-Qwen.IQ3_M.gguf new file mode 100644 index 0000000..f2284b0 --- /dev/null +++ b/Wise-Qwen.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3254cdc1aba4d40042b73dc3ece232f2a6276a206f4a2a75e242ca8d7dc6da0 +size 776289344 diff --git a/Wise-Qwen.IQ3_S.gguf b/Wise-Qwen.IQ3_S.gguf new file mode 100644 index 0000000..41602ea --- /dev/null +++ b/Wise-Qwen.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93de21205799562b3e791d673f711347853b05ac1be2b85fa0475049f95a9dc4 +size 762032192 diff --git a/Wise-Qwen.IQ3_XS.gguf b/Wise-Qwen.IQ3_XS.gguf new file mode 100644 index 0000000..5f89610 --- /dev/null +++ b/Wise-Qwen.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b454487dcf59faf18e2ac2cfa619a7e2375466bb4dc52b982d6c1611f6cf0504 +size 731324480 diff --git a/Wise-Qwen.IQ4_XS.gguf b/Wise-Qwen.IQ4_XS.gguf new file mode 100644 index 0000000..a6e9ca9 --- /dev/null +++ b/Wise-Qwen.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53236934cfb4f242843300911a9307ba2ce2c83d711a93185abe8bf1cd3914e5 +size 901808192 diff --git a/Wise-Qwen.Q2_K.gguf b/Wise-Qwen.Q2_K.gguf new file mode 100644 index 0000000..acc3d9a --- /dev/null +++ b/Wise-Qwen.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f7d738a8b0212ade03fe3fffde871d0c65d070317c0831e6c5a679e28eabbb5 +size 675930176 diff --git a/Wise-Qwen.Q3_K_L.gguf b/Wise-Qwen.Q3_K_L.gguf new file mode 100644 index 0000000..e81f41d --- /dev/null +++ b/Wise-Qwen.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a99802f5294e58a8f8f0cb4965c8269083e96402bb3fcb7152f7f1a8e60647a7 +size 879788096 diff --git a/Wise-Qwen.Q3_K_M.gguf b/Wise-Qwen.Q3_K_M.gguf new file mode 100644 index 0000000..409254e --- /dev/null +++ b/Wise-Qwen.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08b9448e02da8dd4fc8e68e152c941ae0a07ba33628e768e9b96f979cd1223c1 +size 823803968 diff --git a/Wise-Qwen.Q3_K_S.gguf b/Wise-Qwen.Q3_K_S.gguf new file mode 100644 index 0000000..9d58eb1 --- /dev/null +++ b/Wise-Qwen.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc4e5461836667ee434d47cf50a2a5c205542cdb53f467ff2c4f5523b88ff190 +size 760569920 diff --git a/Wise-Qwen.Q4_K_M.gguf b/Wise-Qwen.Q4_K_M.gguf new file mode 100644 index 0000000..c6bb5ba --- /dev/null +++ b/Wise-Qwen.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdb0bbd900c24d6a724c40a528b9199ebc380dded9b5b7171e2f30608800a83c +size 985673792 diff --git a/Wise-Qwen.Q4_K_S.gguf b/Wise-Qwen.Q4_K_S.gguf new file mode 100644 index 0000000..5ef1901 --- /dev/null +++ b/Wise-Qwen.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6324ca8fa46f2d27ba9c5494118fcfff4b211e2fdf89c9fe84e24846cba4d03 +size 939937856 diff --git a/Wise-Qwen.Q5_K_M.gguf b/Wise-Qwen.Q5_K_M.gguf new file mode 100644 index 0000000..60f1596 --- /dev/null +++ b/Wise-Qwen.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09609a67843efb1f4042cab191e10e0fe505632aade1551cf9562581271b6fde +size 1124675648 diff --git a/Wise-Qwen.Q5_K_S.gguf b/Wise-Qwen.Q5_K_S.gguf new file mode 100644 index 0000000..4acbfbb --- /dev/null +++ b/Wise-Qwen.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:837c15c06803dfa8fc0ef164e651855ec52597b577353d050d0e72f8d41fa3b2 +size 1098354752 diff --git a/Wise-Qwen.Q6_K.gguf b/Wise-Qwen.Q6_K.gguf new file mode 100644 index 0000000..f633b1b --- /dev/null +++ b/Wise-Qwen.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:086408b3d9d601adca736314aded28cd8be1de2d4295494af92085035f2abb45 +size 1272365120 diff --git a/Wise-Qwen.Q8_0.gguf b/Wise-Qwen.Q8_0.gguf new file mode 100644 index 0000000..442433f --- /dev/null +++ b/Wise-Qwen.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba99ba5bd421763a9b0238751442cb6bbb721a5ed8ebdd7b0de3434845336042 +size 1646090432 diff --git a/Wise-Qwen.f16.gguf b/Wise-Qwen.f16.gguf new file mode 100644 index 0000000..237c6ed --- /dev/null +++ b/Wise-Qwen.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b348123efe18e9fdbed1e92c72214423cd8f539b31785e69c5652b7bc8bc11e +size 3092769152