commit b0f80af56469282d4dc651d14abe0d0bfffe78c3 Author: ModelHub XC Date: Thu Jun 11 19:38:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Zhongsi-6B-Benchmark-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..21e065b --- /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 +Zhongsi-6B-Benchmark.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Zhongsi-6B-Benchmark.f16.gguf filter=lfs diff=lfs merge=lfs -text +Zhongsi-6B-Benchmark.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Zhongsi-6B-Benchmark.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Zhongsi-6B-Benchmark.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Zhongsi-6B-Benchmark.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Zhongsi-6B-Benchmark.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Zhongsi-6B-Benchmark.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Zhongsi-6B-Benchmark.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Zhongsi-6B-Benchmark.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Zhongsi-6B-Benchmark.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Zhongsi-6B-Benchmark.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a8402fd --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: SYSU-MUCFC-FinTech-Research-Center/Zhongsi-6B-Benchmark +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +tags: +- llama-factory +- full +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/SYSU-MUCFC-FinTech-Research-Center/Zhongsi-6B-Benchmark + + +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/Zhongsi-6B-Benchmark-GGUF/resolve/main/Zhongsi-6B-Benchmark.Q2_K.gguf) | Q2_K | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Zhongsi-6B-Benchmark-GGUF/resolve/main/Zhongsi-6B-Benchmark.Q3_K_S.gguf) | Q3_K_S | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Zhongsi-6B-Benchmark-GGUF/resolve/main/Zhongsi-6B-Benchmark.Q3_K_M.gguf) | Q3_K_M | 3.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Zhongsi-6B-Benchmark-GGUF/resolve/main/Zhongsi-6B-Benchmark.Q3_K_L.gguf) | Q3_K_L | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Zhongsi-6B-Benchmark-GGUF/resolve/main/Zhongsi-6B-Benchmark.IQ4_XS.gguf) | IQ4_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Zhongsi-6B-Benchmark-GGUF/resolve/main/Zhongsi-6B-Benchmark.Q4_K_S.gguf) | Q4_K_S | 3.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Zhongsi-6B-Benchmark-GGUF/resolve/main/Zhongsi-6B-Benchmark.Q4_K_M.gguf) | Q4_K_M | 3.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Zhongsi-6B-Benchmark-GGUF/resolve/main/Zhongsi-6B-Benchmark.Q5_K_S.gguf) | Q5_K_S | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/Zhongsi-6B-Benchmark-GGUF/resolve/main/Zhongsi-6B-Benchmark.Q5_K_M.gguf) | Q5_K_M | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Zhongsi-6B-Benchmark-GGUF/resolve/main/Zhongsi-6B-Benchmark.Q6_K.gguf) | Q6_K | 5.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Zhongsi-6B-Benchmark-GGUF/resolve/main/Zhongsi-6B-Benchmark.Q8_0.gguf) | Q8_0 | 6.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Zhongsi-6B-Benchmark-GGUF/resolve/main/Zhongsi-6B-Benchmark.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. + + diff --git a/Zhongsi-6B-Benchmark.IQ4_XS.gguf b/Zhongsi-6B-Benchmark.IQ4_XS.gguf new file mode 100644 index 0000000..d46105b --- /dev/null +++ b/Zhongsi-6B-Benchmark.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:042208d9bc8d5e4d09eca81715349c229581f567a35b8232db6699abf9863e4e +size 3336787104 diff --git a/Zhongsi-6B-Benchmark.Q2_K.gguf b/Zhongsi-6B-Benchmark.Q2_K.gguf new file mode 100644 index 0000000..caad57b --- /dev/null +++ b/Zhongsi-6B-Benchmark.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6f1040ce97a21153f90d35b01c4c5726e3463cc09504265012cca3399b76ffc +size 2337068192 diff --git a/Zhongsi-6B-Benchmark.Q3_K_L.gguf b/Zhongsi-6B-Benchmark.Q3_K_L.gguf new file mode 100644 index 0000000..cbbfb7d --- /dev/null +++ b/Zhongsi-6B-Benchmark.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcfe099646014e4de70168b2c180367cb0cf6e3f12a99c37a9b4554352d1cd8d +size 3236893856 diff --git a/Zhongsi-6B-Benchmark.Q3_K_M.gguf b/Zhongsi-6B-Benchmark.Q3_K_M.gguf new file mode 100644 index 0000000..fe992a2 --- /dev/null +++ b/Zhongsi-6B-Benchmark.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:878f2511cfb4bb138e403661969ed73aad079af292d2ff9ed054b0f1c0886504 +size 2992837792 diff --git a/Zhongsi-6B-Benchmark.Q3_K_S.gguf b/Zhongsi-6B-Benchmark.Q3_K_S.gguf new file mode 100644 index 0000000..e512a45 --- /dev/null +++ b/Zhongsi-6B-Benchmark.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:513f53cd79d3753abc8adc4c375dd374c9ee53bd6c68f807303652031a85b79e +size 2709197984 diff --git a/Zhongsi-6B-Benchmark.Q4_K_M.gguf b/Zhongsi-6B-Benchmark.Q4_K_M.gguf new file mode 100644 index 0000000..3eb0a8f --- /dev/null +++ b/Zhongsi-6B-Benchmark.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c92f691d703ccb622fd2fb03666ea78929f0d14526f28be5db06c3db813709b +size 3673969824 diff --git a/Zhongsi-6B-Benchmark.Q4_K_S.gguf b/Zhongsi-6B-Benchmark.Q4_K_S.gguf new file mode 100644 index 0000000..a3ed766 --- /dev/null +++ b/Zhongsi-6B-Benchmark.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2c0c9c8cf6595b21af5a43302709b92c33a70fb96340b16d4b680fbf9ed8420 +size 3502920864 diff --git a/Zhongsi-6B-Benchmark.Q5_K_M.gguf b/Zhongsi-6B-Benchmark.Q5_K_M.gguf new file mode 100644 index 0000000..89e203b --- /dev/null +++ b/Zhongsi-6B-Benchmark.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7c6b05ca04cb04c2e5c3c32df4f7dc2e8a1e948b21f5b315d1252972f9da2bc +size 4304426144 diff --git a/Zhongsi-6B-Benchmark.Q5_K_S.gguf b/Zhongsi-6B-Benchmark.Q5_K_S.gguf new file mode 100644 index 0000000..49fa113 --- /dev/null +++ b/Zhongsi-6B-Benchmark.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebe26908a40103588e8dfe699b8955d5ee197bce4461c87442926f06ee10a9ec +size 4204156064 diff --git a/Zhongsi-6B-Benchmark.Q6_K.gguf b/Zhongsi-6B-Benchmark.Q6_K.gguf new file mode 100644 index 0000000..66e92e5 --- /dev/null +++ b/Zhongsi-6B-Benchmark.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0854ed9bb2c72626c7f0ec12eb902e4a2ff8be9dccdf9da69e0d2810fd43ce1e +size 4974285984 diff --git a/Zhongsi-6B-Benchmark.Q8_0.gguf b/Zhongsi-6B-Benchmark.Q8_0.gguf new file mode 100644 index 0000000..6f01c60 --- /dev/null +++ b/Zhongsi-6B-Benchmark.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb4102416f0fea28d1fbacb6a4bd175983029d54bd755bc14c2cb7a094165cc6 +size 6442128544 diff --git a/Zhongsi-6B-Benchmark.f16.gguf b/Zhongsi-6B-Benchmark.f16.gguf new file mode 100644 index 0000000..00a5a4f --- /dev/null +++ b/Zhongsi-6B-Benchmark.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38a240abfa81522ac172e49ecb412c6135e6ee4dd48592bdc036cb4a776a9121 +size 12124099744