commit fc3555698d745b91605449fec4b23c8ee53fdac6 Author: ModelHub XC Date: Thu Jun 11 11:14:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/XuanYuan-6B-Chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3c94523 --- /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-Chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +XuanYuan-6B-Chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +XuanYuan-6B-Chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +XuanYuan-6B-Chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +XuanYuan-6B-Chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +XuanYuan-6B-Chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +XuanYuan-6B-Chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +XuanYuan-6B-Chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +XuanYuan-6B-Chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +XuanYuan-6B-Chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +XuanYuan-6B-Chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +XuanYuan-6B-Chat.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d20bdf7 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: Duxiaoman-DI/XuanYuan-6B-Chat +language: +- en +library_name: transformers +license: llama2 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Duxiaoman-DI/XuanYuan-6B-Chat + + +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-Chat-GGUF/resolve/main/XuanYuan-6B-Chat.Q2_K.gguf) | Q2_K | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/XuanYuan-6B-Chat-GGUF/resolve/main/XuanYuan-6B-Chat.Q3_K_S.gguf) | Q3_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/XuanYuan-6B-Chat-GGUF/resolve/main/XuanYuan-6B-Chat.Q3_K_M.gguf) | Q3_K_M | 3.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/XuanYuan-6B-Chat-GGUF/resolve/main/XuanYuan-6B-Chat.Q3_K_L.gguf) | Q3_K_L | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/XuanYuan-6B-Chat-GGUF/resolve/main/XuanYuan-6B-Chat.IQ4_XS.gguf) | IQ4_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/XuanYuan-6B-Chat-GGUF/resolve/main/XuanYuan-6B-Chat.Q4_K_S.gguf) | Q4_K_S | 3.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/XuanYuan-6B-Chat-GGUF/resolve/main/XuanYuan-6B-Chat.Q4_K_M.gguf) | Q4_K_M | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/XuanYuan-6B-Chat-GGUF/resolve/main/XuanYuan-6B-Chat.Q5_K_S.gguf) | Q5_K_S | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/XuanYuan-6B-Chat-GGUF/resolve/main/XuanYuan-6B-Chat.Q5_K_M.gguf) | Q5_K_M | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/XuanYuan-6B-Chat-GGUF/resolve/main/XuanYuan-6B-Chat.Q6_K.gguf) | Q6_K | 5.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/XuanYuan-6B-Chat-GGUF/resolve/main/XuanYuan-6B-Chat.Q8_0.gguf) | Q8_0 | 6.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/XuanYuan-6B-Chat-GGUF/resolve/main/XuanYuan-6B-Chat.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-Chat.IQ4_XS.gguf b/XuanYuan-6B-Chat.IQ4_XS.gguf new file mode 100644 index 0000000..e930641 --- /dev/null +++ b/XuanYuan-6B-Chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64c7b22d0fc10436c7dcb27cf675cafba4381bf65fd195114b799e9456a492ab +size 3466703232 diff --git a/XuanYuan-6B-Chat.Q2_K.gguf b/XuanYuan-6B-Chat.Q2_K.gguf new file mode 100644 index 0000000..d8245c5 --- /dev/null +++ b/XuanYuan-6B-Chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:489c5cbe5e23df72aed3c7042bb42ee394e9a3188ef49f473d035d57235fddee +size 2419147776 diff --git a/XuanYuan-6B-Chat.Q3_K_L.gguf b/XuanYuan-6B-Chat.Q3_K_L.gguf new file mode 100644 index 0000000..50233cf --- /dev/null +++ b/XuanYuan-6B-Chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c38722ed61889646d305aaf767a394dd9b7e248671f6742dcea5241b38f6231 +size 3420805824 diff --git a/XuanYuan-6B-Chat.Q3_K_M.gguf b/XuanYuan-6B-Chat.Q3_K_M.gguf new file mode 100644 index 0000000..ef61a30 --- /dev/null +++ b/XuanYuan-6B-Chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1392046348553a976be19e797c22c2ba2617743396250f7bc0b37b78b67663a +size 3135724224 diff --git a/XuanYuan-6B-Chat.Q3_K_S.gguf b/XuanYuan-6B-Chat.Q3_K_S.gguf new file mode 100644 index 0000000..8179d94 --- /dev/null +++ b/XuanYuan-6B-Chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c86a9dd93c9f411ed14101a3132b0a34ec0b48053d79e8259ea0273d12eff278 +size 2812549824 diff --git a/XuanYuan-6B-Chat.Q4_K_M.gguf b/XuanYuan-6B-Chat.Q4_K_M.gguf new file mode 100644 index 0000000..90624b3 --- /dev/null +++ b/XuanYuan-6B-Chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b49889df899a649b2be96860030edf394c609ab789e9c74c3c5f9c9b90c89e0 +size 3863640192 diff --git a/XuanYuan-6B-Chat.Q4_K_S.gguf b/XuanYuan-6B-Chat.Q4_K_S.gguf new file mode 100644 index 0000000..2208885 --- /dev/null +++ b/XuanYuan-6B-Chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:865eeb4e38b15a93a88c2f145473dbbf5a24cbb3c206b2994ca30230f7fc55ce +size 3665639552 diff --git a/XuanYuan-6B-Chat.Q5_K_M.gguf b/XuanYuan-6B-Chat.Q5_K_M.gguf new file mode 100644 index 0000000..dff0439 --- /dev/null +++ b/XuanYuan-6B-Chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88db211c66aa3b646b180bc1ad324afac63d6106e47a63772cfbae2486e4cde3 +size 4534473856 diff --git a/XuanYuan-6B-Chat.Q5_K_S.gguf b/XuanYuan-6B-Chat.Q5_K_S.gguf new file mode 100644 index 0000000..23f1332 --- /dev/null +++ b/XuanYuan-6B-Chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d9418a9c01c80a1364793407220ddad359597c343b42e643aa3414bf0dc38f6 +size 4419441792 diff --git a/XuanYuan-6B-Chat.Q6_K.gguf b/XuanYuan-6B-Chat.Q6_K.gguf new file mode 100644 index 0000000..c7669a2 --- /dev/null +++ b/XuanYuan-6B-Chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56df59bc2b593f5d0800abf7c5a3e52e18e45655632f12823711e0713aca16ed +size 5247234624 diff --git a/XuanYuan-6B-Chat.Q8_0.gguf b/XuanYuan-6B-Chat.Q8_0.gguf new file mode 100644 index 0000000..dab1b3e --- /dev/null +++ b/XuanYuan-6B-Chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96335d89dc0dda844cbb1828cbf89eff8cd2248a9f485d7cf096808e42559b37 +size 6795861696 diff --git a/XuanYuan-6B-Chat.f16.gguf b/XuanYuan-6B-Chat.f16.gguf new file mode 100644 index 0000000..c85c50b --- /dev/null +++ b/XuanYuan-6B-Chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f4036d6b1e3f9ae98fb0a6eec400da05847f6d623fc69c29b2d61497bced5b5 +size 12790547136