commit a89fce5846d972655bfaf7493e29bf0c119bdd5e Author: ModelHub XC Date: Mon Oct 12 07:45:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SanGuoYanYi-6b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..90045eb --- /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 +SanGuoYanYi-6b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SanGuoYanYi-6b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SanGuoYanYi-6b.f16.gguf filter=lfs diff=lfs merge=lfs -text +SanGuoYanYi-6b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SanGuoYanYi-6b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SanGuoYanYi-6b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SanGuoYanYi-6b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SanGuoYanYi-6b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SanGuoYanYi-6b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SanGuoYanYi-6b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SanGuoYanYi-6b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SanGuoYanYi-6b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..7a89aa7 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: stylellm/SanGuoYanYi-6b +language: +- zh +library_name: transformers +license: other +license_link: https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE +license_name: yi-license +quantized_by: mradermacher +tags: +- text-style-transfer +- literature +--- +## About + + + + + + +static quants of https://huggingface.co/stylellm/SanGuoYanYi-6b + + +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/SanGuoYanYi-6b-GGUF/resolve/main/SanGuoYanYi-6b.Q2_K.gguf) | Q2_K | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/SanGuoYanYi-6b-GGUF/resolve/main/SanGuoYanYi-6b.Q3_K_S.gguf) | Q3_K_S | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/SanGuoYanYi-6b-GGUF/resolve/main/SanGuoYanYi-6b.Q3_K_M.gguf) | Q3_K_M | 3.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SanGuoYanYi-6b-GGUF/resolve/main/SanGuoYanYi-6b.Q3_K_L.gguf) | Q3_K_L | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/SanGuoYanYi-6b-GGUF/resolve/main/SanGuoYanYi-6b.IQ4_XS.gguf) | IQ4_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/SanGuoYanYi-6b-GGUF/resolve/main/SanGuoYanYi-6b.Q4_K_S.gguf) | Q4_K_S | 3.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SanGuoYanYi-6b-GGUF/resolve/main/SanGuoYanYi-6b.Q4_K_M.gguf) | Q4_K_M | 3.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SanGuoYanYi-6b-GGUF/resolve/main/SanGuoYanYi-6b.Q5_K_S.gguf) | Q5_K_S | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/SanGuoYanYi-6b-GGUF/resolve/main/SanGuoYanYi-6b.Q5_K_M.gguf) | Q5_K_M | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/SanGuoYanYi-6b-GGUF/resolve/main/SanGuoYanYi-6b.Q6_K.gguf) | Q6_K | 5.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SanGuoYanYi-6b-GGUF/resolve/main/SanGuoYanYi-6b.Q8_0.gguf) | Q8_0 | 6.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SanGuoYanYi-6b-GGUF/resolve/main/SanGuoYanYi-6b.f16.gguf) | f16 | 12.2 | 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. 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. + + diff --git a/SanGuoYanYi-6b.IQ4_XS.gguf b/SanGuoYanYi-6b.IQ4_XS.gguf new file mode 100644 index 0000000..5d3a6c2 --- /dev/null +++ b/SanGuoYanYi-6b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b841aae4c326229565aace54b8ffe1a87d4d9d0c2e0963bbbd85d49575b776c +size 3336786464 diff --git a/SanGuoYanYi-6b.Q2_K.gguf b/SanGuoYanYi-6b.Q2_K.gguf new file mode 100644 index 0000000..adfcf03 --- /dev/null +++ b/SanGuoYanYi-6b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f11b3080f1a7b781f37aee0a5dd73ec17e8a7c7e68f0c08b08f881df4699e1f +size 2337067552 diff --git a/SanGuoYanYi-6b.Q3_K_L.gguf b/SanGuoYanYi-6b.Q3_K_L.gguf new file mode 100644 index 0000000..3bd14ad --- /dev/null +++ b/SanGuoYanYi-6b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fbee4b404971933103d596e3ea6d1b5b6cfd0f4af2b4bb071cc2d8d82942620 +size 3236893216 diff --git a/SanGuoYanYi-6b.Q3_K_M.gguf b/SanGuoYanYi-6b.Q3_K_M.gguf new file mode 100644 index 0000000..f628152 --- /dev/null +++ b/SanGuoYanYi-6b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e5d884baa3feca79f5c6de968dcf187aaa088692d39bf68e8c3fe6646fe912b +size 2992837152 diff --git a/SanGuoYanYi-6b.Q3_K_S.gguf b/SanGuoYanYi-6b.Q3_K_S.gguf new file mode 100644 index 0000000..9da58dd --- /dev/null +++ b/SanGuoYanYi-6b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bf03f310588327ca9f8725f5eaaae7a6bf49f1ff0d2326c36eabb2fe2b7c0d6 +size 2709197344 diff --git a/SanGuoYanYi-6b.Q4_K_M.gguf b/SanGuoYanYi-6b.Q4_K_M.gguf new file mode 100644 index 0000000..43f86ed --- /dev/null +++ b/SanGuoYanYi-6b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f17a6264c8acc70484e8cc90c1dc13087153dc47c7f3d77eac363c6b6d477bc9 +size 3673969184 diff --git a/SanGuoYanYi-6b.Q4_K_S.gguf b/SanGuoYanYi-6b.Q4_K_S.gguf new file mode 100644 index 0000000..59a100d --- /dev/null +++ b/SanGuoYanYi-6b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f52cf6bbe880587e6c239da6909e728ccc88ff81528a5e18cfbc45b20f893722 +size 3502920224 diff --git a/SanGuoYanYi-6b.Q5_K_M.gguf b/SanGuoYanYi-6b.Q5_K_M.gguf new file mode 100644 index 0000000..d26c274 --- /dev/null +++ b/SanGuoYanYi-6b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e5a24f5aaf581dfc6adb304e750d60310490a1d3fc250b59e8e4c084b1d7e3e +size 4304425504 diff --git a/SanGuoYanYi-6b.Q5_K_S.gguf b/SanGuoYanYi-6b.Q5_K_S.gguf new file mode 100644 index 0000000..6245d97 --- /dev/null +++ b/SanGuoYanYi-6b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5922f83f71b9896d1d0cf167d890821114e0951c3e4631dc9ddf06c9363e38c0 +size 4204155424 diff --git a/SanGuoYanYi-6b.Q6_K.gguf b/SanGuoYanYi-6b.Q6_K.gguf new file mode 100644 index 0000000..62c14a7 --- /dev/null +++ b/SanGuoYanYi-6b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91ae8b1397de59c344a8dfaf790ed420f90222c0a5d7fd194456953d6334bd01 +size 4974285344 diff --git a/SanGuoYanYi-6b.Q8_0.gguf b/SanGuoYanYi-6b.Q8_0.gguf new file mode 100644 index 0000000..57ba1db --- /dev/null +++ b/SanGuoYanYi-6b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a8076c1812dac9d355ece4efb9fcf9417d495bc7f0d444ce593b7c1b9fdec28 +size 6442127904 diff --git a/SanGuoYanYi-6b.f16.gguf b/SanGuoYanYi-6b.f16.gguf new file mode 100644 index 0000000..e86b449 --- /dev/null +++ b/SanGuoYanYi-6b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9e4a38b197bfd943fad025b6f6168c40b739afeba628135fdfa9b48feaf6e72 +size 12124099104