commit e0307de402a40a1cab497efb925e2ec9fa7843f4 Author: ModelHub XC Date: Tue Jul 21 18:33:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/mistral-7b-arc_reasoning-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b9d492c --- /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 +mistral-7b-arc_reasoning.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-arc_reasoning.f16.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-arc_reasoning.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-arc_reasoning.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-arc_reasoning.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-arc_reasoning.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-arc_reasoning.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-arc_reasoning.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-arc_reasoning.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-arc_reasoning.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-arc_reasoning.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-arc_reasoning.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e1ae47d --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: bany1111/mistral-7b-arc_reasoning +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- mistral +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/bany1111/mistral-7b-arc_reasoning + + +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/mistral-7b-arc_reasoning-GGUF/resolve/main/mistral-7b-arc_reasoning.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-arc_reasoning-GGUF/resolve/main/mistral-7b-arc_reasoning.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-arc_reasoning-GGUF/resolve/main/mistral-7b-arc_reasoning.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-arc_reasoning-GGUF/resolve/main/mistral-7b-arc_reasoning.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-arc_reasoning-GGUF/resolve/main/mistral-7b-arc_reasoning.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-arc_reasoning-GGUF/resolve/main/mistral-7b-arc_reasoning.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-arc_reasoning-GGUF/resolve/main/mistral-7b-arc_reasoning.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-arc_reasoning-GGUF/resolve/main/mistral-7b-arc_reasoning.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-arc_reasoning-GGUF/resolve/main/mistral-7b-arc_reasoning.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-arc_reasoning-GGUF/resolve/main/mistral-7b-arc_reasoning.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-arc_reasoning-GGUF/resolve/main/mistral-7b-arc_reasoning.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-arc_reasoning-GGUF/resolve/main/mistral-7b-arc_reasoning.f16.gguf) | f16 | 14.6 | 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/mistral-7b-arc_reasoning.IQ4_XS.gguf b/mistral-7b-arc_reasoning.IQ4_XS.gguf new file mode 100644 index 0000000..9b1535d --- /dev/null +++ b/mistral-7b-arc_reasoning.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8498f9b450c4fce254dca0ab2b03041351f52cfb997fe22ab9356d3a30276a3 +size 3944389728 diff --git a/mistral-7b-arc_reasoning.Q2_K.gguf b/mistral-7b-arc_reasoning.Q2_K.gguf new file mode 100644 index 0000000..9a8a1f8 --- /dev/null +++ b/mistral-7b-arc_reasoning.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:111fa76950da8d5ffe5fd49dfe91598d7da299c622afd863ec37b00147034a1a +size 2719243360 diff --git a/mistral-7b-arc_reasoning.Q3_K_L.gguf b/mistral-7b-arc_reasoning.Q3_K_L.gguf new file mode 100644 index 0000000..64fe0a7 --- /dev/null +++ b/mistral-7b-arc_reasoning.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d76e346d371154f7619a46f7da00bc8cc6a336578f81bc185fba6773a19d43f +size 3822025824 diff --git a/mistral-7b-arc_reasoning.Q3_K_M.gguf b/mistral-7b-arc_reasoning.Q3_K_M.gguf new file mode 100644 index 0000000..ef71716 --- /dev/null +++ b/mistral-7b-arc_reasoning.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f621e70b60934f6138395d99d66f6b1343029adb13f2e133f11e94aba52ccd9 +size 3518987360 diff --git a/mistral-7b-arc_reasoning.Q3_K_S.gguf b/mistral-7b-arc_reasoning.Q3_K_S.gguf new file mode 100644 index 0000000..6513aae --- /dev/null +++ b/mistral-7b-arc_reasoning.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a25759a5ab157a4af6e5c7b407107f7dcbff729fa25381f95ec83b7cc5aece36 +size 3164568672 diff --git a/mistral-7b-arc_reasoning.Q4_K_M.gguf b/mistral-7b-arc_reasoning.Q4_K_M.gguf new file mode 100644 index 0000000..0e575d4 --- /dev/null +++ b/mistral-7b-arc_reasoning.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:006b405b4c683019d5b7a3d7ddd10756cf0e8f841c5f469b69067e2c1ae920de +size 4368440416 diff --git a/mistral-7b-arc_reasoning.Q4_K_S.gguf b/mistral-7b-arc_reasoning.Q4_K_S.gguf new file mode 100644 index 0000000..51d8e4a --- /dev/null +++ b/mistral-7b-arc_reasoning.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b3e77d1b7272ef17f4b1014e514ca3013cf862a210c97a960d4c29590142f5f +size 4140375136 diff --git a/mistral-7b-arc_reasoning.Q5_K_M.gguf b/mistral-7b-arc_reasoning.Q5_K_M.gguf new file mode 100644 index 0000000..f2a9fe9 --- /dev/null +++ b/mistral-7b-arc_reasoning.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:477606cacae41a8a58cf0048d834398d03eedb71b3481854d45c918c13682405 +size 5131410528 diff --git a/mistral-7b-arc_reasoning.Q5_K_S.gguf b/mistral-7b-arc_reasoning.Q5_K_S.gguf new file mode 100644 index 0000000..09de222 --- /dev/null +++ b/mistral-7b-arc_reasoning.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63c3aa279a20e7861b605cadecdb54cadf82b941b897478f816553eec6fc82f1 +size 4997717088 diff --git a/mistral-7b-arc_reasoning.Q6_K.gguf b/mistral-7b-arc_reasoning.Q6_K.gguf new file mode 100644 index 0000000..59f6020 --- /dev/null +++ b/mistral-7b-arc_reasoning.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6795c0300ae4a239ea3953138407d3fe3007477210d4ec2bea1aef2d276b2d8 +size 5942066272 diff --git a/mistral-7b-arc_reasoning.Q8_0.gguf b/mistral-7b-arc_reasoning.Q8_0.gguf new file mode 100644 index 0000000..8892cae --- /dev/null +++ b/mistral-7b-arc_reasoning.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:355ea372e4906d50c3e42700a46b3807ad1c3e6cadabc5d178f64b9bb77c0a29 +size 7695858784 diff --git a/mistral-7b-arc_reasoning.f16.gguf b/mistral-7b-arc_reasoning.f16.gguf new file mode 100644 index 0000000..48726ec --- /dev/null +++ b/mistral-7b-arc_reasoning.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75f7de9d6770aea5f71bccdd3f1fc9a8b9fbf2de1340eba62b22f3fef4964bce +size 14484733024