commit c1b88da815e8b349fa6d7a4755cddc1f4b74c092 Author: ModelHub XC Date: Sun May 10 07:28:34 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/BenchHub-Cat-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..56e0070 --- /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 +BenchHub-Cat-7b.f16.gguf filter=lfs diff=lfs merge=lfs -text +BenchHub-Cat-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BenchHub-Cat-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +BenchHub-Cat-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +BenchHub-Cat-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +BenchHub-Cat-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BenchHub-Cat-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BenchHub-Cat-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +BenchHub-Cat-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BenchHub-Cat-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BenchHub-Cat-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BenchHub-Cat-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/BenchHub-Cat-7b.IQ4_XS.gguf b/BenchHub-Cat-7b.IQ4_XS.gguf new file mode 100644 index 0000000..3ef3ccb --- /dev/null +++ b/BenchHub-Cat-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94dd096a1ad6b92796afa6f0e570657aa12e05603b49e24138e39dd364fd0874 +size 4248357056 diff --git a/BenchHub-Cat-7b.Q2_K.gguf b/BenchHub-Cat-7b.Q2_K.gguf new file mode 100644 index 0000000..84609f5 --- /dev/null +++ b/BenchHub-Cat-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:857e6a7a0caa5be16cd9d622cf183e2d9d79b376a0fea22c4dd1ab2acfcc8c06 +size 3014289248 diff --git a/BenchHub-Cat-7b.Q3_K_L.gguf b/BenchHub-Cat-7b.Q3_K_L.gguf new file mode 100644 index 0000000..56744a0 --- /dev/null +++ b/BenchHub-Cat-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a24829102bcf6a85025b4587d9c22d99c55c0fcf487ffae98c26d2ade86777d +size 4086663200 diff --git a/BenchHub-Cat-7b.Q3_K_M.gguf b/BenchHub-Cat-7b.Q3_K_M.gguf new file mode 100644 index 0000000..f085e1b --- /dev/null +++ b/BenchHub-Cat-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe3a5923b3f6845e8013855cf49116dbf55c50bcf85205047a7ea84dca6198b2 +size 3806595104 diff --git a/BenchHub-Cat-7b.Q3_K_S.gguf b/BenchHub-Cat-7b.Q3_K_S.gguf new file mode 100644 index 0000000..8aa0195 --- /dev/null +++ b/BenchHub-Cat-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:568d0e54c987c6753e44de3395afe40703da3a9214a0dd58100479aae2533564 +size 3490572320 diff --git a/BenchHub-Cat-7b.Q4_K_M.gguf b/BenchHub-Cat-7b.Q4_K_M.gguf new file mode 100644 index 0000000..d8e5583 --- /dev/null +++ b/BenchHub-Cat-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81c097b42477a5aae80b4ae1115ccfc54039141e4e6fa8ff47a3f2aaef47a8e0 +size 4681087520 diff --git a/BenchHub-Cat-7b.Q4_K_S.gguf b/BenchHub-Cat-7b.Q4_K_S.gguf new file mode 100644 index 0000000..33e0187 --- /dev/null +++ b/BenchHub-Cat-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86203c8d220511a7cf585c5263d7953d0a58cfc70eebd244da9988b929483ac7 +size 4455782944 diff --git a/BenchHub-Cat-7b.Q5_K_M.gguf b/BenchHub-Cat-7b.Q5_K_M.gguf new file mode 100644 index 0000000..54a8727 --- /dev/null +++ b/BenchHub-Cat-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:769bae6d3876e507c7ad24d512a9b4eb30a1e9da3d692bf164178e7f1c52d0d0 +size 5442666464 diff --git a/BenchHub-Cat-7b.Q5_K_S.gguf b/BenchHub-Cat-7b.Q5_K_S.gguf new file mode 100644 index 0000000..86def68 --- /dev/null +++ b/BenchHub-Cat-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82be1c5eb21b510a9626398ee3d6893bd9ba5812743ce9d11ecbcc50ec58507b +size 5313011680 diff --git a/BenchHub-Cat-7b.Q6_K.gguf b/BenchHub-Cat-7b.Q6_K.gguf new file mode 100644 index 0000000..178fe79 --- /dev/null +++ b/BenchHub-Cat-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99bd25204a2c06476ec47f074e0ba726ad3f67ba90906917ab2040184712900b +size 6251844096 diff --git a/BenchHub-Cat-7b.Q8_0.gguf b/BenchHub-Cat-7b.Q8_0.gguf new file mode 100644 index 0000000..05abd93 --- /dev/null +++ b/BenchHub-Cat-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:296de5e3902ac4ea7189f2e5251263f9a042205ccda458c5dd6908da5423bceb +size 8095477824 diff --git a/BenchHub-Cat-7b.f16.gguf b/BenchHub-Cat-7b.f16.gguf new file mode 100644 index 0000000..8dc3397 --- /dev/null +++ b/BenchHub-Cat-7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8040c54ac0aacfab2223466b6499c2241f4fa06bbae6fc0320c1f5e2ba01cd7 +size 15232124544 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ed6f107 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: BenchHub/BenchHub-Cat-7b +datasets: +- custom +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- LLM +- classification +- instruction-tuned +- multi-label +- qwen +--- +## About + + + + + + +static quants of https://huggingface.co/BenchHub/BenchHub-Cat-7b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#BenchHub-Cat-7b-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/BenchHub-Cat-7b-i1-GGUF +## 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/BenchHub-Cat-7b-GGUF/resolve/main/BenchHub-Cat-7b.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/BenchHub-Cat-7b-GGUF/resolve/main/BenchHub-Cat-7b.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/BenchHub-Cat-7b-GGUF/resolve/main/BenchHub-Cat-7b.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/BenchHub-Cat-7b-GGUF/resolve/main/BenchHub-Cat-7b.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/BenchHub-Cat-7b-GGUF/resolve/main/BenchHub-Cat-7b.IQ4_XS.gguf) | IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/BenchHub-Cat-7b-GGUF/resolve/main/BenchHub-Cat-7b.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BenchHub-Cat-7b-GGUF/resolve/main/BenchHub-Cat-7b.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BenchHub-Cat-7b-GGUF/resolve/main/BenchHub-Cat-7b.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/BenchHub-Cat-7b-GGUF/resolve/main/BenchHub-Cat-7b.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/BenchHub-Cat-7b-GGUF/resolve/main/BenchHub-Cat-7b.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/BenchHub-Cat-7b-GGUF/resolve/main/BenchHub-Cat-7b.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/BenchHub-Cat-7b-GGUF/resolve/main/BenchHub-Cat-7b.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. + +