commit 0ba5e3f8e620fc57e513c450d135ed125dfcaae0 Author: ModelHub XC Date: Fri Jun 12 23:26:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/mistral-7b-grok-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a36053c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,51 @@ +*.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-grok.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-grok.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-grok.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-grok.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-grok.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-grok.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-grok.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-grok.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-grok.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-grok.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-grok.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-grok.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-grok.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-grok.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-grok.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-grok.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..c8ca0fc --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: HuggingFaceH4/mistral-7b-grok +datasets: +- HuggingFaceH4/grok-conversation-harmless +- HuggingFaceH4/ultrachat_200k +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- alignment-handbook +- generated_from_trainer +--- +## About + +static quants of https://huggingface.co/HuggingFaceH4/mistral-7b-grok + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/mistral-7b-grok-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/mistral-7b-grok-GGUF/resolve/main/mistral-7b-grok.Q2_K.gguf) | Q2_K | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-grok-GGUF/resolve/main/mistral-7b-grok.IQ3_XS.gguf) | IQ3_XS | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-grok-GGUF/resolve/main/mistral-7b-grok.Q3_K_S.gguf) | Q3_K_S | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-grok-GGUF/resolve/main/mistral-7b-grok.IQ3_S.gguf) | IQ3_S | 3.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-grok-GGUF/resolve/main/mistral-7b-grok.IQ3_M.gguf) | IQ3_M | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-grok-GGUF/resolve/main/mistral-7b-grok.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-grok-GGUF/resolve/main/mistral-7b-grok.Q3_K_L.gguf) | Q3_K_L | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-grok-GGUF/resolve/main/mistral-7b-grok.IQ4_XS.gguf) | IQ4_XS | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-grok-GGUF/resolve/main/mistral-7b-grok.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-grok-GGUF/resolve/main/mistral-7b-grok.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-grok-GGUF/resolve/main/mistral-7b-grok.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-grok-GGUF/resolve/main/mistral-7b-grok.Q5_K_S.gguf) | Q5_K_S | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-grok-GGUF/resolve/main/mistral-7b-grok.Q5_K_M.gguf) | Q5_K_M | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-grok-GGUF/resolve/main/mistral-7b-grok.Q6_K.gguf) | Q6_K | 6.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-grok-GGUF/resolve/main/mistral-7b-grok.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/mistral-7b-grok-GGUF/resolve/main/mistral-7b-grok.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-grok.IQ3_M.gguf b/mistral-7b-grok.IQ3_M.gguf new file mode 100644 index 0000000..e0a6e70 --- /dev/null +++ b/mistral-7b-grok.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f2d66917e91fff3df566d2f0319801c54b2117bb4ddb0e7cf4e969427f20e59 +size 3439515840 diff --git a/mistral-7b-grok.IQ3_S.gguf b/mistral-7b-grok.IQ3_S.gguf new file mode 100644 index 0000000..d91b99b --- /dev/null +++ b/mistral-7b-grok.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8886130b5c748a159b376294efe1f9965c2548d73b39c592ff0800d60b02fcd3 +size 3337017536 diff --git a/mistral-7b-grok.IQ3_XS.gguf b/mistral-7b-grok.IQ3_XS.gguf new file mode 100644 index 0000000..b610afe --- /dev/null +++ b/mistral-7b-grok.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7712aa30a74aaf543e4de3c6e3553e508ea690b30db02fb9775e124751b7efb9 +size 3155613888 diff --git a/mistral-7b-grok.IQ4_XS.gguf b/mistral-7b-grok.IQ4_XS.gguf new file mode 100644 index 0000000..34925e8 --- /dev/null +++ b/mistral-7b-grok.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4d3b791a2189b0231f58d2427992fcd31e8fde1fcbdccab1c362988c8760a0e +size 4099012800 diff --git a/mistral-7b-grok.Q2_K.gguf b/mistral-7b-grok.Q2_K.gguf new file mode 100644 index 0000000..8190d67 --- /dev/null +++ b/mistral-7b-grok.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ec13e0b9832da8b94476eee5b5882a5fa945a6b2a814c982ec4b1bc3848132b +size 2873866432 diff --git a/mistral-7b-grok.Q3_K_L.gguf b/mistral-7b-grok.Q3_K_L.gguf new file mode 100644 index 0000000..a272efa --- /dev/null +++ b/mistral-7b-grok.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1612bff76426594d4b5a656cad52a76c2b6bd244981b54049eb8ec883935743 +size 3976648896 diff --git a/mistral-7b-grok.Q3_K_M.gguf b/mistral-7b-grok.Q3_K_M.gguf new file mode 100644 index 0000000..6d04aa1 --- /dev/null +++ b/mistral-7b-grok.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03f43f1574a02dd4648258395d7f58e58bdb07ea35f3309dd1a70ea94e3ac8ef +size 3673610432 diff --git a/mistral-7b-grok.Q3_K_S.gguf b/mistral-7b-grok.Q3_K_S.gguf new file mode 100644 index 0000000..6cca836 --- /dev/null +++ b/mistral-7b-grok.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c55908112c12fbdbd5b67b6f2d5fdf949a2a9501401c5096ba7982b7ea3eefb3 +size 3319191744 diff --git a/mistral-7b-grok.Q4_0_4_4.gguf b/mistral-7b-grok.Q4_0_4_4.gguf new file mode 100644 index 0000000..fc2d39d --- /dev/null +++ b/mistral-7b-grok.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7f049ee9457ddebd18721fa584962dc0e1eb05192f1783d813694bf2f42a8b8 +size 4108918656 diff --git a/mistral-7b-grok.Q4_K_M.gguf b/mistral-7b-grok.Q4_K_M.gguf new file mode 100644 index 0000000..62625ac --- /dev/null +++ b/mistral-7b-grok.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c68cb8ea05bc9dc5a5299fe364b110ba79d560a38db2eb8502cfb47d56267a81 +size 4523063488 diff --git a/mistral-7b-grok.Q4_K_S.gguf b/mistral-7b-grok.Q4_K_S.gguf new file mode 100644 index 0000000..76ee795 --- /dev/null +++ b/mistral-7b-grok.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:720d1d133ead22bc760a3f2906a16c2a45a4b5bba703c0be9249133edd80dcfa +size 4294998208 diff --git a/mistral-7b-grok.Q5_K_M.gguf b/mistral-7b-grok.Q5_K_M.gguf new file mode 100644 index 0000000..2f15c60 --- /dev/null +++ b/mistral-7b-grok.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e6ddfc385b342bb974ef6fe4eb1dab2aa08d167254a9e10915dc4a8b28e61ae +size 5286033600 diff --git a/mistral-7b-grok.Q5_K_S.gguf b/mistral-7b-grok.Q5_K_S.gguf new file mode 100644 index 0000000..2b2715b --- /dev/null +++ b/mistral-7b-grok.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc2211ff1548a0b570b1dd8f6eec6e2121f64dca4598a1f8936438ae6afda198 +size 5152340160 diff --git a/mistral-7b-grok.Q6_K.gguf b/mistral-7b-grok.Q6_K.gguf new file mode 100644 index 0000000..07db8e0 --- /dev/null +++ b/mistral-7b-grok.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:870a925e9ab932ca5dfbe83fdd3d335125ed7bc3cb0030882391ac1953c1dc44 +size 6096689344 diff --git a/mistral-7b-grok.Q8_0.gguf b/mistral-7b-grok.Q8_0.gguf new file mode 100644 index 0000000..1cb8628 --- /dev/null +++ b/mistral-7b-grok.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08d2399ce54e2edea2b8a4fb051e0104ecd5c771db82598c8e9d712a45536ba4 +size 7818737856 diff --git a/mistral-7b-grok.f16.gguf b/mistral-7b-grok.f16.gguf new file mode 100644 index 0000000..44cdb1e --- /dev/null +++ b/mistral-7b-grok.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a23586b191095b87d0310c5890351874ae01c765c3628f5996e62a9fd44b4831 +size 14484733824