commit b7cd28566075608654366cd2eebf77b3780f2e41 Author: ModelHub XC Date: Mon May 4 15:26:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DistillQwen-ThoughtY-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7558fb2 --- /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 +DistillQwen-ThoughtY-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DistillQwen-ThoughtY-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DistillQwen-ThoughtY-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DistillQwen-ThoughtY-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DistillQwen-ThoughtY-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DistillQwen-ThoughtY-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DistillQwen-ThoughtY-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +DistillQwen-ThoughtY-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DistillQwen-ThoughtY-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DistillQwen-ThoughtY-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DistillQwen-ThoughtY-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DistillQwen-ThoughtY-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DistillQwen-ThoughtY-8B.IQ4_XS.gguf b/DistillQwen-ThoughtY-8B.IQ4_XS.gguf new file mode 100644 index 0000000..e3f6849 --- /dev/null +++ b/DistillQwen-ThoughtY-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:025cfa242dc59c5de0e86e6aea6b136fddcd0da7beea24c5c85914888f7d744e +size 4593296704 diff --git a/DistillQwen-ThoughtY-8B.Q2_K.gguf b/DistillQwen-ThoughtY-8B.Q2_K.gguf new file mode 100644 index 0000000..5d51c1b --- /dev/null +++ b/DistillQwen-ThoughtY-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edc372194b03896b44e51d49289ab4196c6ca83403f112b5863cdf879b8116ec +size 3281732928 diff --git a/DistillQwen-ThoughtY-8B.Q3_K_L.gguf b/DistillQwen-ThoughtY-8B.Q3_K_L.gguf new file mode 100644 index 0000000..db333fc --- /dev/null +++ b/DistillQwen-ThoughtY-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bff0954267598eb38341038084283e320cf8eb5a79212f21917ca0c63a684d8 +size 4431394112 diff --git a/DistillQwen-ThoughtY-8B.Q3_K_M.gguf b/DistillQwen-ThoughtY-8B.Q3_K_M.gguf new file mode 100644 index 0000000..043fd3e --- /dev/null +++ b/DistillQwen-ThoughtY-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b326efcf8bd39e8511c1736f10a72e6422013d4e0582485c7a12cc32be5aa45 +size 4124161344 diff --git a/DistillQwen-ThoughtY-8B.Q3_K_S.gguf b/DistillQwen-ThoughtY-8B.Q3_K_S.gguf new file mode 100644 index 0000000..896956e --- /dev/null +++ b/DistillQwen-ThoughtY-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14ad1bedce54db7a07d7ef62eb90843e71698b0b90eb5736979536fc2a96d661 +size 3769611584 diff --git a/DistillQwen-ThoughtY-8B.Q4_K_M.gguf b/DistillQwen-ThoughtY-8B.Q4_K_M.gguf new file mode 100644 index 0000000..40c3137 --- /dev/null +++ b/DistillQwen-ThoughtY-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbe1cb29dc58f6b3f6fe0ffe3e0158e3f6a6cc40920950d6f99fbfff322cee7b +size 5027784000 diff --git a/DistillQwen-ThoughtY-8B.Q4_K_S.gguf b/DistillQwen-ThoughtY-8B.Q4_K_S.gguf new file mode 100644 index 0000000..c1be224 --- /dev/null +++ b/DistillQwen-ThoughtY-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f14f22c115e1f152a525e3bf0c9db1f07fe0c1236ff9b16ede965a4345b75f8d +size 4802012480 diff --git a/DistillQwen-ThoughtY-8B.Q5_K_M.gguf b/DistillQwen-ThoughtY-8B.Q5_K_M.gguf new file mode 100644 index 0000000..436f07e --- /dev/null +++ b/DistillQwen-ThoughtY-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19acd57346cd8ab8d5a18730f081c677de810921b20e16f3ea5562a8f4ac49e0 +size 5851112768 diff --git a/DistillQwen-ThoughtY-8B.Q5_K_S.gguf b/DistillQwen-ThoughtY-8B.Q5_K_S.gguf new file mode 100644 index 0000000..de8eeef --- /dev/null +++ b/DistillQwen-ThoughtY-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b24b69c60dc276b7d4a40a591155bf8cebd1a14965e915feb2b0cd721116d477 +size 5720761664 diff --git a/DistillQwen-ThoughtY-8B.Q6_K.gguf b/DistillQwen-ThoughtY-8B.Q6_K.gguf new file mode 100644 index 0000000..6aa3fbe --- /dev/null +++ b/DistillQwen-ThoughtY-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb0578f1e12a6f631747ce8136543cacec29a72692a30ff2f07c840c847d1000 +size 6725899584 diff --git a/DistillQwen-ThoughtY-8B.Q8_0.gguf b/DistillQwen-ThoughtY-8B.Q8_0.gguf new file mode 100644 index 0000000..bb0c601 --- /dev/null +++ b/DistillQwen-ThoughtY-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe71fada3ee102afcb3d8424700fd08d8a42912d1d59c14e0b55e92022f863ec +size 8709518656 diff --git a/DistillQwen-ThoughtY-8B.f16.gguf b/DistillQwen-ThoughtY-8B.f16.gguf new file mode 100644 index 0000000..c40701c --- /dev/null +++ b/DistillQwen-ThoughtY-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ce3b27d4584cccd0ba76a91fa2ab91ca9765b8ef557e5daa1daf8ffdffa668d +size 16388044096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7365e87 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: alibaba-pai/DistillQwen-ThoughtY-8B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/alibaba-pai/DistillQwen-ThoughtY-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/DistillQwen-ThoughtY-8B-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/DistillQwen-ThoughtY-8B-GGUF/resolve/main/DistillQwen-ThoughtY-8B.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/DistillQwen-ThoughtY-8B-GGUF/resolve/main/DistillQwen-ThoughtY-8B.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/DistillQwen-ThoughtY-8B-GGUF/resolve/main/DistillQwen-ThoughtY-8B.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DistillQwen-ThoughtY-8B-GGUF/resolve/main/DistillQwen-ThoughtY-8B.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/DistillQwen-ThoughtY-8B-GGUF/resolve/main/DistillQwen-ThoughtY-8B.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/DistillQwen-ThoughtY-8B-GGUF/resolve/main/DistillQwen-ThoughtY-8B.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DistillQwen-ThoughtY-8B-GGUF/resolve/main/DistillQwen-ThoughtY-8B.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DistillQwen-ThoughtY-8B-GGUF/resolve/main/DistillQwen-ThoughtY-8B.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/DistillQwen-ThoughtY-8B-GGUF/resolve/main/DistillQwen-ThoughtY-8B.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/DistillQwen-ThoughtY-8B-GGUF/resolve/main/DistillQwen-ThoughtY-8B.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DistillQwen-ThoughtY-8B-GGUF/resolve/main/DistillQwen-ThoughtY-8B.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DistillQwen-ThoughtY-8B-GGUF/resolve/main/DistillQwen-ThoughtY-8B.f16.gguf) | f16 | 16.5 | 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. + +