commit ad8375368470114dd6bfdbed90a2452e1ad36e65 Author: ModelHub XC Date: Sun Apr 12 13:40:58 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mistral-7B-Instruct-v0.2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7ec541c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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-Instruct-v0.2.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mistral-7B-Instruct-v0.2.IQ3_M.gguf b/Mistral-7B-Instruct-v0.2.IQ3_M.gguf new file mode 100644 index 0000000..3364547 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5173ca4e1bba857cf7288219471d022ef99ef76b894681a6fba426c861cfe6d +size 3284893376 diff --git a/Mistral-7B-Instruct-v0.2.IQ3_S.gguf b/Mistral-7B-Instruct-v0.2.IQ3_S.gguf new file mode 100644 index 0000000..eb0f33f --- /dev/null +++ b/Mistral-7B-Instruct-v0.2.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:206eea540952cdd761abfc7659e1726df933abc524e82f38e4776971e3ead5d8 +size 3182395072 diff --git a/Mistral-7B-Instruct-v0.2.IQ3_XS.gguf b/Mistral-7B-Instruct-v0.2.IQ3_XS.gguf new file mode 100644 index 0000000..8709f78 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9517863fa3857e9f1279e8597ae40694415baedb45c39382f051409317745123 +size 3018817216 diff --git a/Mistral-7B-Instruct-v0.2.IQ4_XS.gguf b/Mistral-7B-Instruct-v0.2.IQ4_XS.gguf new file mode 100644 index 0000000..4c94ea8 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bee70327c2b29cd6c6b0060eaf18e533d7f59cb61c0e305ebd367b9de3946500 +size 3944390336 diff --git a/Mistral-7B-Instruct-v0.2.Q2_K.gguf b/Mistral-7B-Instruct-v0.2.Q2_K.gguf new file mode 100644 index 0000000..6f722a0 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d57a459cb0be34ac876b8b70ae7fe12ff99d59631d498951106165e15c257131 +size 2719243968 diff --git a/Mistral-7B-Instruct-v0.2.Q3_K_L.gguf b/Mistral-7B-Instruct-v0.2.Q3_K_L.gguf new file mode 100644 index 0000000..7b902c9 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c299e82ceed21e49e8092b8512276886b51c3ecbb1399d563b42e37b83235ba3 +size 3822026432 diff --git a/Mistral-7B-Instruct-v0.2.Q3_K_M.gguf b/Mistral-7B-Instruct-v0.2.Q3_K_M.gguf new file mode 100644 index 0000000..3ad2ecd --- /dev/null +++ b/Mistral-7B-Instruct-v0.2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fc850050a09976e473eedf795bf69135d0e0f600c4c0a26cd9cfcd42a900598 +size 3518987968 diff --git a/Mistral-7B-Instruct-v0.2.Q3_K_S.gguf b/Mistral-7B-Instruct-v0.2.Q3_K_S.gguf new file mode 100644 index 0000000..c0bee6c --- /dev/null +++ b/Mistral-7B-Instruct-v0.2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7b5a969f3d724a55d8a44ebded6a85be10bc1f5385c47030988a7b817a90173 +size 3164569280 diff --git a/Mistral-7B-Instruct-v0.2.Q4_K_M.gguf b/Mistral-7B-Instruct-v0.2.Q4_K_M.gguf new file mode 100644 index 0000000..aa302d5 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2d7044c02b0ce9bce2ef8f37fb5bbab0190b774515473613400627b6f49f321 +size 4368441024 diff --git a/Mistral-7B-Instruct-v0.2.Q4_K_S.gguf b/Mistral-7B-Instruct-v0.2.Q4_K_S.gguf new file mode 100644 index 0000000..45c0105 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:930d976797d93c743ee66f3b97b5f269fd99e24cabb9845d702ddb53cd87242b +size 4140375744 diff --git a/Mistral-7B-Instruct-v0.2.Q5_K_M.gguf b/Mistral-7B-Instruct-v0.2.Q5_K_M.gguf new file mode 100644 index 0000000..5e49aeb --- /dev/null +++ b/Mistral-7B-Instruct-v0.2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87aefb361dcc8690a6d3e227e77e8944a9a6bb2a18fc405b7c3209468cc557b2 +size 5131411136 diff --git a/Mistral-7B-Instruct-v0.2.Q5_K_S.gguf b/Mistral-7B-Instruct-v0.2.Q5_K_S.gguf new file mode 100644 index 0000000..5f3fc9e --- /dev/null +++ b/Mistral-7B-Instruct-v0.2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e81030d5ac0cac9d5dca6d3b193c9dbe5676378bd76e77a43f4930af8cebded9 +size 4997717696 diff --git a/Mistral-7B-Instruct-v0.2.Q6_K.gguf b/Mistral-7B-Instruct-v0.2.Q6_K.gguf new file mode 100644 index 0000000..2a61708 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06cba6fc656615ef68504362c7a6b42a4803e7b85259eef44e21726fe7d8d049 +size 5942066880 diff --git a/Mistral-7B-Instruct-v0.2.Q8_0.gguf b/Mistral-7B-Instruct-v0.2.Q8_0.gguf new file mode 100644 index 0000000..3c18467 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ea33b47c1519cf70798fb3115c8f9bdc2635210174941fc7955ba3e7cddb668 +size 7695859392 diff --git a/README.md b/README.md new file mode 100644 index 0000000..dc8619b --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: mistralai/Mistral-7B-Instruct-v0.2 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- finetuned +- mistral-common +--- +## About + + + + + + +static quants of https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Mistral-7B-Instruct-v0.2-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-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-Instruct-v0.2-GGUF/resolve/main/Mistral-7B-Instruct-v0.2.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-GGUF/resolve/main/Mistral-7B-Instruct-v0.2.IQ3_XS.gguf) | IQ3_XS | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-GGUF/resolve/main/Mistral-7B-Instruct-v0.2.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-GGUF/resolve/main/Mistral-7B-Instruct-v0.2.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-GGUF/resolve/main/Mistral-7B-Instruct-v0.2.IQ3_M.gguf) | IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-GGUF/resolve/main/Mistral-7B-Instruct-v0.2.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-GGUF/resolve/main/Mistral-7B-Instruct-v0.2.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-GGUF/resolve/main/Mistral-7B-Instruct-v0.2.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-GGUF/resolve/main/Mistral-7B-Instruct-v0.2.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-GGUF/resolve/main/Mistral-7B-Instruct-v0.2.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-GGUF/resolve/main/Mistral-7B-Instruct-v0.2.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-GGUF/resolve/main/Mistral-7B-Instruct-v0.2.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-GGUF/resolve/main/Mistral-7B-Instruct-v0.2.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-GGUF/resolve/main/Mistral-7B-Instruct-v0.2.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | + +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. + +