commit be9ef112354bae78e24ce1acef21b4fccad974d1 Author: ModelHub XC Date: Sat Jul 11 22:02:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OpenMath-Mistral-7B-v0.1-hf-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..65b5b02 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +OpenMath-Mistral-7B-v0.1-hf.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenMath-Mistral-7B-v0.1-hf.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenMath-Mistral-7B-v0.1-hf.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenMath-Mistral-7B-v0.1-hf.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenMath-Mistral-7B-v0.1-hf.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenMath-Mistral-7B-v0.1-hf.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OpenMath-Mistral-7B-v0.1-hf.f16.gguf filter=lfs diff=lfs merge=lfs -text +OpenMath-Mistral-7B-v0.1-hf.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OpenMath-Mistral-7B-v0.1-hf.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenMath-Mistral-7B-v0.1-hf.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenMath-Mistral-7B-v0.1-hf.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenMath-Mistral-7B-v0.1-hf.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +OpenMath-Mistral-7B-v0.1-hf.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OpenMath-Mistral-7B-v0.1-hf.IQ4_XS.gguf b/OpenMath-Mistral-7B-v0.1-hf.IQ4_XS.gguf new file mode 100644 index 0000000..8b27c33 --- /dev/null +++ b/OpenMath-Mistral-7B-v0.1-hf.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4bce5b4ae04d64517c77debc172a23c2b105c110cd30ba501411eac51c71397 +size 3944389632 diff --git a/OpenMath-Mistral-7B-v0.1-hf.Q2_K.gguf b/OpenMath-Mistral-7B-v0.1-hf.Q2_K.gguf new file mode 100644 index 0000000..c923def --- /dev/null +++ b/OpenMath-Mistral-7B-v0.1-hf.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f04eda7c024d1ff89cdb970c335bbf1fefa3ef48e5aeed19566342f018be722e +size 2719243264 diff --git a/OpenMath-Mistral-7B-v0.1-hf.Q3_K_L.gguf b/OpenMath-Mistral-7B-v0.1-hf.Q3_K_L.gguf new file mode 100644 index 0000000..a5127e7 --- /dev/null +++ b/OpenMath-Mistral-7B-v0.1-hf.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49023817efe36e023e0fbc2084cd6434d8a127a54572f9a2667f05022d5df9a2 +size 3822025728 diff --git a/OpenMath-Mistral-7B-v0.1-hf.Q3_K_M.gguf b/OpenMath-Mistral-7B-v0.1-hf.Q3_K_M.gguf new file mode 100644 index 0000000..4f27aa0 --- /dev/null +++ b/OpenMath-Mistral-7B-v0.1-hf.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0ef0d857546d8d5750d6fc45260c5244148bfd539e128fbe3aaf5769c74e7b3 +size 3518987264 diff --git a/OpenMath-Mistral-7B-v0.1-hf.Q3_K_S.gguf b/OpenMath-Mistral-7B-v0.1-hf.Q3_K_S.gguf new file mode 100644 index 0000000..1ce4d0e --- /dev/null +++ b/OpenMath-Mistral-7B-v0.1-hf.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de5abc4769172d42dd1815237bb9121dc2b58bba824e82c29e6cf6a784c9289f +size 3164568576 diff --git a/OpenMath-Mistral-7B-v0.1-hf.Q4_0_4_4.gguf b/OpenMath-Mistral-7B-v0.1-hf.Q4_0_4_4.gguf new file mode 100644 index 0000000..d1ed64a --- /dev/null +++ b/OpenMath-Mistral-7B-v0.1-hf.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03a9edb84d59f58f4393ab10feebdd7dc68f27d4a8cfd48002383ea0baf94d35 +size 4108917760 diff --git a/OpenMath-Mistral-7B-v0.1-hf.Q4_K_M.gguf b/OpenMath-Mistral-7B-v0.1-hf.Q4_K_M.gguf new file mode 100644 index 0000000..13291aa --- /dev/null +++ b/OpenMath-Mistral-7B-v0.1-hf.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b17043340b9b09d9e55bb122fc4f2bbc85eccbdef618c336a29f3045c915cc5a +size 4368440320 diff --git a/OpenMath-Mistral-7B-v0.1-hf.Q4_K_S.gguf b/OpenMath-Mistral-7B-v0.1-hf.Q4_K_S.gguf new file mode 100644 index 0000000..ecc8c20 --- /dev/null +++ b/OpenMath-Mistral-7B-v0.1-hf.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ff7d45554331d3fe2ce62586393d089b7fe46c31e69962998bbcf86b2c96926 +size 4140375040 diff --git a/OpenMath-Mistral-7B-v0.1-hf.Q5_K_M.gguf b/OpenMath-Mistral-7B-v0.1-hf.Q5_K_M.gguf new file mode 100644 index 0000000..4da84b8 --- /dev/null +++ b/OpenMath-Mistral-7B-v0.1-hf.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9d5d218ee46e6827e4d5d87922363a0b7e76a6af7024010bf4227f62c5f70a4 +size 5131410432 diff --git a/OpenMath-Mistral-7B-v0.1-hf.Q5_K_S.gguf b/OpenMath-Mistral-7B-v0.1-hf.Q5_K_S.gguf new file mode 100644 index 0000000..9feb3e9 --- /dev/null +++ b/OpenMath-Mistral-7B-v0.1-hf.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21ed99ce1f51d9acc2e7b60151810e5307194da90f699105da8198c330c62bb5 +size 4997716992 diff --git a/OpenMath-Mistral-7B-v0.1-hf.Q6_K.gguf b/OpenMath-Mistral-7B-v0.1-hf.Q6_K.gguf new file mode 100644 index 0000000..561d66b --- /dev/null +++ b/OpenMath-Mistral-7B-v0.1-hf.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b5e27f2787cfb86f19d04c671cca6e7c6f64a018cecf7ac2c71dc6e4875f6dc +size 5942066176 diff --git a/OpenMath-Mistral-7B-v0.1-hf.Q8_0.gguf b/OpenMath-Mistral-7B-v0.1-hf.Q8_0.gguf new file mode 100644 index 0000000..7716a2d --- /dev/null +++ b/OpenMath-Mistral-7B-v0.1-hf.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ec8f29a52559715fb3b4f6b2389f03c38a17eea2e0a1ed1376fd76b7bbd9461 +size 7695858688 diff --git a/OpenMath-Mistral-7B-v0.1-hf.f16.gguf b/OpenMath-Mistral-7B-v0.1-hf.f16.gguf new file mode 100644 index 0000000..b848c35 --- /dev/null +++ b/OpenMath-Mistral-7B-v0.1-hf.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65c35993734d489a7e7abbc6ba2d5009ada37eb4da1c7bdce6e01426841cfa1d +size 14484732928 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0e9f82e --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: nvidia/OpenMath-Mistral-7B-v0.1-hf +datasets: +- nvidia/OpenMathInstruct-1 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- nvidia +- code +- math +--- +## About + + + + + + +static quants of https://huggingface.co/nvidia/OpenMath-Mistral-7B-v0.1-hf + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/OpenMath-Mistral-7B-v0.1-hf-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/OpenMath-Mistral-7B-v0.1-hf-GGUF/resolve/main/OpenMath-Mistral-7B-v0.1-hf.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/OpenMath-Mistral-7B-v0.1-hf-GGUF/resolve/main/OpenMath-Mistral-7B-v0.1-hf.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/OpenMath-Mistral-7B-v0.1-hf-GGUF/resolve/main/OpenMath-Mistral-7B-v0.1-hf.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OpenMath-Mistral-7B-v0.1-hf-GGUF/resolve/main/OpenMath-Mistral-7B-v0.1-hf.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/OpenMath-Mistral-7B-v0.1-hf-GGUF/resolve/main/OpenMath-Mistral-7B-v0.1-hf.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/OpenMath-Mistral-7B-v0.1-hf-GGUF/resolve/main/OpenMath-Mistral-7B-v0.1-hf.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/OpenMath-Mistral-7B-v0.1-hf-GGUF/resolve/main/OpenMath-Mistral-7B-v0.1-hf.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenMath-Mistral-7B-v0.1-hf-GGUF/resolve/main/OpenMath-Mistral-7B-v0.1-hf.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenMath-Mistral-7B-v0.1-hf-GGUF/resolve/main/OpenMath-Mistral-7B-v0.1-hf.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/OpenMath-Mistral-7B-v0.1-hf-GGUF/resolve/main/OpenMath-Mistral-7B-v0.1-hf.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/OpenMath-Mistral-7B-v0.1-hf-GGUF/resolve/main/OpenMath-Mistral-7B-v0.1-hf.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/OpenMath-Mistral-7B-v0.1-hf-GGUF/resolve/main/OpenMath-Mistral-7B-v0.1-hf.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/OpenMath-Mistral-7B-v0.1-hf-GGUF/resolve/main/OpenMath-Mistral-7B-v0.1-hf.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. + +