commit 7e41f24b0a6174c7bd8b6b0aaf1210c63e40a00f Author: ModelHub XC Date: Tue Apr 28 06:11:03 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AutoTrain-Qwen-Rui-Elite-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..06d39e6 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +AutoTrain-Qwen-Rui-Elite.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AutoTrain-Qwen-Rui-Elite.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AutoTrain-Qwen-Rui-Elite.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AutoTrain-Qwen-Rui-Elite.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AutoTrain-Qwen-Rui-Elite.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AutoTrain-Qwen-Rui-Elite.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AutoTrain-Qwen-Rui-Elite.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AutoTrain-Qwen-Rui-Elite.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AutoTrain-Qwen-Rui-Elite.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AutoTrain-Qwen-Rui-Elite.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AutoTrain-Qwen-Rui-Elite.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +AutoTrain-Qwen-Rui-Elite.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +AutoTrain-Qwen-Rui-Elite.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AutoTrain-Qwen-Rui-Elite.IQ4_XS.gguf b/AutoTrain-Qwen-Rui-Elite.IQ4_XS.gguf new file mode 100644 index 0000000..8e9c39f --- /dev/null +++ b/AutoTrain-Qwen-Rui-Elite.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c327ea6195600db69b14546e5ed3d1346a863dfc449876eea05a6f16ea4acb2f +size 4248374560 diff --git a/AutoTrain-Qwen-Rui-Elite.Q2_K.gguf b/AutoTrain-Qwen-Rui-Elite.Q2_K.gguf new file mode 100644 index 0000000..7611ab7 --- /dev/null +++ b/AutoTrain-Qwen-Rui-Elite.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:208e802839f5c3038a604b198852b1c693ab332d67900e319d4330df6113f533 +size 3014303840 diff --git a/AutoTrain-Qwen-Rui-Elite.Q3_K_L.gguf b/AutoTrain-Qwen-Rui-Elite.Q3_K_L.gguf new file mode 100644 index 0000000..5fb15f4 --- /dev/null +++ b/AutoTrain-Qwen-Rui-Elite.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:173e42661c3c9586c274e97043261f29c24e8e811d14138b54b647849bfd4706 +size 4086679232 diff --git a/AutoTrain-Qwen-Rui-Elite.Q3_K_M.gguf b/AutoTrain-Qwen-Rui-Elite.Q3_K_M.gguf new file mode 100644 index 0000000..48c2ef0 --- /dev/null +++ b/AutoTrain-Qwen-Rui-Elite.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48abe4bb26a1354b61bab6bfe5216e976ad2c38f94db44f5f9486407350eeb3c +size 3806611136 diff --git a/AutoTrain-Qwen-Rui-Elite.Q3_K_S.gguf b/AutoTrain-Qwen-Rui-Elite.Q3_K_S.gguf new file mode 100644 index 0000000..e5d4568 --- /dev/null +++ b/AutoTrain-Qwen-Rui-Elite.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c3eb1eeff7a131509bb0bc167f103a56c1952d6f6b2b00613036fe8f61030b5 +size 3490588352 diff --git a/AutoTrain-Qwen-Rui-Elite.Q4_0_4_4.gguf b/AutoTrain-Qwen-Rui-Elite.Q4_0_4_4.gguf new file mode 100644 index 0000000..e39c3f2 --- /dev/null +++ b/AutoTrain-Qwen-Rui-Elite.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7142c547a9d3c9654d348bf196df41fc539f5138cb3a878a7dc9767b2a5205a4 +size 4429422656 diff --git a/AutoTrain-Qwen-Rui-Elite.Q4_K_M.gguf b/AutoTrain-Qwen-Rui-Elite.Q4_K_M.gguf new file mode 100644 index 0000000..cd45bfd --- /dev/null +++ b/AutoTrain-Qwen-Rui-Elite.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e68cee3d532e395467303b8722b97629fb38bf85095b3fcf72fc58ccdeb19bbf +size 4681105472 diff --git a/AutoTrain-Qwen-Rui-Elite.Q4_K_S.gguf b/AutoTrain-Qwen-Rui-Elite.Q4_K_S.gguf new file mode 100644 index 0000000..68ae950 --- /dev/null +++ b/AutoTrain-Qwen-Rui-Elite.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f34615d82d07fecc077f58b4f524e5562f5bdfbb5b7e53c5c8e12d0f5f4beeb +size 4455800896 diff --git a/AutoTrain-Qwen-Rui-Elite.Q5_K_M.gguf b/AutoTrain-Qwen-Rui-Elite.Q5_K_M.gguf new file mode 100644 index 0000000..3c6458f --- /dev/null +++ b/AutoTrain-Qwen-Rui-Elite.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eba24e6a02a7b254b4fd4c0842dcf2b8140f62ce5f5d73e996b8df440142204e +size 5442686208 diff --git a/AutoTrain-Qwen-Rui-Elite.Q5_K_S.gguf b/AutoTrain-Qwen-Rui-Elite.Q5_K_S.gguf new file mode 100644 index 0000000..23bc713 --- /dev/null +++ b/AutoTrain-Qwen-Rui-Elite.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fe19537253051a78ac9e61da98f68ad529473e684aadb70438ef5314450fdfc +size 5313031424 diff --git a/AutoTrain-Qwen-Rui-Elite.Q6_K.gguf b/AutoTrain-Qwen-Rui-Elite.Q6_K.gguf new file mode 100644 index 0000000..39b260d --- /dev/null +++ b/AutoTrain-Qwen-Rui-Elite.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d1119e484ee51fbc08d7ce336223482f446ad9ee802e5d1518df9de77365886 +size 6251865760 diff --git a/AutoTrain-Qwen-Rui-Elite.Q8_0.gguf b/AutoTrain-Qwen-Rui-Elite.Q8_0.gguf new file mode 100644 index 0000000..e10fb13 --- /dev/null +++ b/AutoTrain-Qwen-Rui-Elite.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00b41b1f8dfa042f0335a74704cab9fd168a141c2225f8c191ce1a40ddde171b +size 8095506400 diff --git a/AutoTrain-Qwen-Rui-Elite.f16.gguf b/AutoTrain-Qwen-Rui-Elite.f16.gguf new file mode 100644 index 0000000..d14f4e3 --- /dev/null +++ b/AutoTrain-Qwen-Rui-Elite.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38a6bff5bf0a45e3764f830f4e1b7cac89e3ae46c090b4f4e7862bed7d3f111c +size 15232180000 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b1ffdd8 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Uynaity/AutoTrain-Qwen-Rui-Elite +datasets: +- Uynaity/Rui-Pro +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +tags: +- autotrain +- text-generation-inference +- text-generation +- peft +--- +## About + + + + + + +static quants of https://huggingface.co/Uynaity/AutoTrain-Qwen-Rui-Elite + + +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/AutoTrain-Qwen-Rui-Elite-GGUF/resolve/main/AutoTrain-Qwen-Rui-Elite.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/AutoTrain-Qwen-Rui-Elite-GGUF/resolve/main/AutoTrain-Qwen-Rui-Elite.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/AutoTrain-Qwen-Rui-Elite-GGUF/resolve/main/AutoTrain-Qwen-Rui-Elite.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AutoTrain-Qwen-Rui-Elite-GGUF/resolve/main/AutoTrain-Qwen-Rui-Elite.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/AutoTrain-Qwen-Rui-Elite-GGUF/resolve/main/AutoTrain-Qwen-Rui-Elite.IQ4_XS.gguf) | IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/AutoTrain-Qwen-Rui-Elite-GGUF/resolve/main/AutoTrain-Qwen-Rui-Elite.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.5 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/AutoTrain-Qwen-Rui-Elite-GGUF/resolve/main/AutoTrain-Qwen-Rui-Elite.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AutoTrain-Qwen-Rui-Elite-GGUF/resolve/main/AutoTrain-Qwen-Rui-Elite.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AutoTrain-Qwen-Rui-Elite-GGUF/resolve/main/AutoTrain-Qwen-Rui-Elite.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/AutoTrain-Qwen-Rui-Elite-GGUF/resolve/main/AutoTrain-Qwen-Rui-Elite.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/AutoTrain-Qwen-Rui-Elite-GGUF/resolve/main/AutoTrain-Qwen-Rui-Elite.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/AutoTrain-Qwen-Rui-Elite-GGUF/resolve/main/AutoTrain-Qwen-Rui-Elite.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/AutoTrain-Qwen-Rui-Elite-GGUF/resolve/main/AutoTrain-Qwen-Rui-Elite.f16.gguf) | f16 | 15.3 | 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. + +