commit 90549a7eb12548a896e5abd294b1c54f081e5c7b Author: ModelHub XC Date: Mon Jul 13 17:56:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mistral_Pro_8B_v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5c8f4a2 --- /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_Pro_8B_v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mistral_Pro_8B_v0.1.IQ4_XS.gguf b/Mistral_Pro_8B_v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..5cfd579 --- /dev/null +++ b/Mistral_Pro_8B_v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ccbdabe8ccd2a590340a858f0b937585c89b47fd1dd8bc164ebf774e4420513 +size 4886015488 diff --git a/Mistral_Pro_8B_v0.1.Q2_K.gguf b/Mistral_Pro_8B_v0.1.Q2_K.gguf new file mode 100644 index 0000000..771fa5f --- /dev/null +++ b/Mistral_Pro_8B_v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d84a917f9177f1c8e536cbabe981e283dbce6ad38a7163e96aeb72628620710 +size 3361238528 diff --git a/Mistral_Pro_8B_v0.1.Q3_K_L.gguf b/Mistral_Pro_8B_v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..25a8a28 --- /dev/null +++ b/Mistral_Pro_8B_v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:306289472ff5dfb4c2eb2393009cc95b8d31f623a6a7770b87476524f64f926e +size 4736388608 diff --git a/Mistral_Pro_8B_v0.1.Q3_K_M.gguf b/Mistral_Pro_8B_v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..b62382a --- /dev/null +++ b/Mistral_Pro_8B_v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:808398689a08334173a6021d92fa3f5b3d320c4771e8873b8333c047147ff931 +size 4353658368 diff --git a/Mistral_Pro_8B_v0.1.Q3_K_S.gguf b/Mistral_Pro_8B_v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..2b83089 --- /dev/null +++ b/Mistral_Pro_8B_v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cab669b84380159dc9cf1060a81195d2c4ba1dfdf2aff51f6f5d61bc0fcf0578 +size 3914567168 diff --git a/Mistral_Pro_8B_v0.1.Q4_K_M.gguf b/Mistral_Pro_8B_v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..4201bcb --- /dev/null +++ b/Mistral_Pro_8B_v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af2e6e99c394d141da0e4bec4c81a177cfacc2de4aad97766f99185b5580fdab +size 5415054848 diff --git a/Mistral_Pro_8B_v0.1.Q4_K_S.gguf b/Mistral_Pro_8B_v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..300e8d8 --- /dev/null +++ b/Mistral_Pro_8B_v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8789939afd13c4a2f0e444a1c1d7dfe7c07548672e8641d5111f1d26b17b4d69 +size 5129448960 diff --git a/Mistral_Pro_8B_v0.1.Q5_K_M.gguf b/Mistral_Pro_8B_v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..e8a2426 --- /dev/null +++ b/Mistral_Pro_8B_v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c90c5247460b53d11b42939d29f5d1c0bc5b0aa6761d86d2a89f0bed89f43f8 +size 6364671488 diff --git a/Mistral_Pro_8B_v0.1.Q5_K_S.gguf b/Mistral_Pro_8B_v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..1d44750 --- /dev/null +++ b/Mistral_Pro_8B_v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55ab5177fc0b8bfa56ebe44b8b68ce78a57a6f2cadaffdf1b986a4ff611c4350 +size 6197554688 diff --git a/Mistral_Pro_8B_v0.1.Q6_K.gguf b/Mistral_Pro_8B_v0.1.Q6_K.gguf new file mode 100644 index 0000000..5aa0150 --- /dev/null +++ b/Mistral_Pro_8B_v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b57a5d4d92babd1cfbaf930ee44702945a896bab047615df5f9fa196ee96186 +size 7373639168 diff --git a/Mistral_Pro_8B_v0.1.Q8_0.gguf b/Mistral_Pro_8B_v0.1.Q8_0.gguf new file mode 100644 index 0000000..99923f0 --- /dev/null +++ b/Mistral_Pro_8B_v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2cf4db10a45b2932175665e604c5ece86cd3d2c4e69a2d84009a5f6cd9ac8a6 +size 9550007808 diff --git a/Mistral_Pro_8B_v0.1.f16.gguf b/Mistral_Pro_8B_v0.1.f16.gguf new file mode 100644 index 0000000..f40e0be --- /dev/null +++ b/Mistral_Pro_8B_v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9227adf16647683226493f94733dad23f7cf35fa5dad732cd2dcfd48821bf0b1 +size 17974660608 diff --git a/README.md b/README.md new file mode 100644 index 0000000..afc852b --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: TencentARC/Mistral_Pro_8B_v0.1 +datasets: +- HuggingFaceTB/cosmopedia +- EleutherAI/proof-pile-2 +- bigcode/the-stack-dedup +- math-ai/AutoMathText +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/TencentARC/Mistral_Pro_8B_v0.1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-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_Pro_8B_v0.1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.Q2_K.gguf) | Q2_K | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.Q3_K_S.gguf) | Q3_K_S | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.Q3_K_M.gguf) | Q3_K_M | 4.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.Q3_K_L.gguf) | Q3_K_L | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.IQ4_XS.gguf) | IQ4_XS | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.Q4_K_S.gguf) | Q4_K_S | 5.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.Q4_K_M.gguf) | Q4_K_M | 5.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.Q5_K_S.gguf) | Q5_K_S | 6.3 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.Q5_K_M.gguf) | Q5_K_M | 6.5 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.Q6_K.gguf) | Q6_K | 7.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.Q8_0.gguf) | Q8_0 | 9.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.f16.gguf) | f16 | 18.1 | 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. + +