commit b8ac2826d4a28a095976ffacdb03014e9c7d279a Author: ModelHub XC Date: Tue Sep 1 17:48:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/XuanYuan-6B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4348651 --- /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 +XuanYuan-6B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +XuanYuan-6B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +XuanYuan-6B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +XuanYuan-6B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +XuanYuan-6B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +XuanYuan-6B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +XuanYuan-6B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +XuanYuan-6B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +XuanYuan-6B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +XuanYuan-6B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +XuanYuan-6B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +XuanYuan-6B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5ea4f47 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: Duxiaoman-DI/XuanYuan-6B +language: +- en +library_name: transformers +license: llama2 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Duxiaoman-DI/XuanYuan-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/XuanYuan-6B-GGUF/resolve/main/XuanYuan-6B.Q2_K.gguf) | Q2_K | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/XuanYuan-6B-GGUF/resolve/main/XuanYuan-6B.Q3_K_S.gguf) | Q3_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/XuanYuan-6B-GGUF/resolve/main/XuanYuan-6B.Q3_K_M.gguf) | Q3_K_M | 3.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/XuanYuan-6B-GGUF/resolve/main/XuanYuan-6B.Q3_K_L.gguf) | Q3_K_L | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/XuanYuan-6B-GGUF/resolve/main/XuanYuan-6B.IQ4_XS.gguf) | IQ4_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/XuanYuan-6B-GGUF/resolve/main/XuanYuan-6B.Q4_K_S.gguf) | Q4_K_S | 3.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/XuanYuan-6B-GGUF/resolve/main/XuanYuan-6B.Q4_K_M.gguf) | Q4_K_M | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/XuanYuan-6B-GGUF/resolve/main/XuanYuan-6B.Q5_K_S.gguf) | Q5_K_S | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/XuanYuan-6B-GGUF/resolve/main/XuanYuan-6B.Q5_K_M.gguf) | Q5_K_M | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/XuanYuan-6B-GGUF/resolve/main/XuanYuan-6B.Q6_K.gguf) | Q6_K | 5.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/XuanYuan-6B-GGUF/resolve/main/XuanYuan-6B.Q8_0.gguf) | Q8_0 | 6.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/XuanYuan-6B-GGUF/resolve/main/XuanYuan-6B.f16.gguf) | f16 | 12.9 | 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/XuanYuan-6B.IQ4_XS.gguf b/XuanYuan-6B.IQ4_XS.gguf new file mode 100644 index 0000000..8d304f1 --- /dev/null +++ b/XuanYuan-6B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67b17e68867602996b284b625bbd5445901088a09f680e3bcccaee25010232da +size 3466703072 diff --git a/XuanYuan-6B.Q2_K.gguf b/XuanYuan-6B.Q2_K.gguf new file mode 100644 index 0000000..2b411d6 --- /dev/null +++ b/XuanYuan-6B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:287e1d485308520bff13ae74fdd042d7c1f8960644dd3d707708ec0101471b1e +size 2419147616 diff --git a/XuanYuan-6B.Q3_K_L.gguf b/XuanYuan-6B.Q3_K_L.gguf new file mode 100644 index 0000000..64c4f34 --- /dev/null +++ b/XuanYuan-6B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e08b72bb5d5116494811c5518640cb0786186dd3a06600af023e7ae8cf62ccd8 +size 3420805664 diff --git a/XuanYuan-6B.Q3_K_M.gguf b/XuanYuan-6B.Q3_K_M.gguf new file mode 100644 index 0000000..0c502e4 --- /dev/null +++ b/XuanYuan-6B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e00f1f6351f87f99d7b780d0709f70351974682994055961e283aa23d8eb06d1 +size 3135724064 diff --git a/XuanYuan-6B.Q3_K_S.gguf b/XuanYuan-6B.Q3_K_S.gguf new file mode 100644 index 0000000..6e2e762 --- /dev/null +++ b/XuanYuan-6B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a72be92d49e951ac828fa748d7c3c9e09e1590edb7bcc7f2de2c814dc5e1a00 +size 2812549664 diff --git a/XuanYuan-6B.Q4_K_M.gguf b/XuanYuan-6B.Q4_K_M.gguf new file mode 100644 index 0000000..3a19599 --- /dev/null +++ b/XuanYuan-6B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3032763d29404764d7123823abbafcef2319062509e84359ac329e8f79341e6 +size 3863640032 diff --git a/XuanYuan-6B.Q4_K_S.gguf b/XuanYuan-6B.Q4_K_S.gguf new file mode 100644 index 0000000..b23e9cb --- /dev/null +++ b/XuanYuan-6B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa18373cffbdb34bcaffa076ee8001c50b383a5a939ed5958460ad59b1fe2e1a +size 3665639392 diff --git a/XuanYuan-6B.Q5_K_M.gguf b/XuanYuan-6B.Q5_K_M.gguf new file mode 100644 index 0000000..0c36e20 --- /dev/null +++ b/XuanYuan-6B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4c1ec0b061d477666a2019ead0a4441808365b6849ca9fa4b92d5bcf1d31f81 +size 4534473696 diff --git a/XuanYuan-6B.Q5_K_S.gguf b/XuanYuan-6B.Q5_K_S.gguf new file mode 100644 index 0000000..e424f4e --- /dev/null +++ b/XuanYuan-6B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4b2de85259045e843e9378a815f9552006bb33f5dce71ad8d3da21e6fdb5580 +size 4419441632 diff --git a/XuanYuan-6B.Q6_K.gguf b/XuanYuan-6B.Q6_K.gguf new file mode 100644 index 0000000..16d2baa --- /dev/null +++ b/XuanYuan-6B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd7e8452f2b69f71416b7f6fb1c6574e5670c19925c4a1157e1110eb0c773601 +size 5247234464 diff --git a/XuanYuan-6B.Q8_0.gguf b/XuanYuan-6B.Q8_0.gguf new file mode 100644 index 0000000..e16f90d --- /dev/null +++ b/XuanYuan-6B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78347fc1cbb0c25145f74c12d899d5fb3106b5ba381179047abe19aa4a96f22a +size 6795861536 diff --git a/XuanYuan-6B.f16.gguf b/XuanYuan-6B.f16.gguf new file mode 100644 index 0000000..e7d36e9 --- /dev/null +++ b/XuanYuan-6B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f1656fd8e19b0c504f3d1444f7d627459f05c286d6edcaade4b68bb2968e37f +size 12790546976