commit 2e450e298d90804082ad116d458d857cb91678d2 Author: ModelHub XC Date: Sun Oct 11 18:15:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mistral-7B-compressed-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..268a508 --- /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-compressed.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-compressed.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-compressed.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-compressed.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-compressed.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-compressed.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-compressed.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-compressed.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-compressed.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-compressed.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-compressed.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-compressed.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mistral-7B-compressed.IQ4_XS.gguf b/Mistral-7B-compressed.IQ4_XS.gguf new file mode 100644 index 0000000..a7e14e4 --- /dev/null +++ b/Mistral-7B-compressed.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c888810528aeabc118e31c3170b9641e74f9a7c2b2e924f25d0b332e0724353 +size 3944389440 diff --git a/Mistral-7B-compressed.Q2_K.gguf b/Mistral-7B-compressed.Q2_K.gguf new file mode 100644 index 0000000..ab9c78f --- /dev/null +++ b/Mistral-7B-compressed.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b3400f472a48807db2004ab0612e5c9d62f5e5667235101ec6daa682cb0e608 +size 2719243072 diff --git a/Mistral-7B-compressed.Q3_K_L.gguf b/Mistral-7B-compressed.Q3_K_L.gguf new file mode 100644 index 0000000..3dde045 --- /dev/null +++ b/Mistral-7B-compressed.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8a48d14a2d1bbaf46087be2600d83e4bb542f8dc4af24f882761a6c83c1c6b1 +size 3822025536 diff --git a/Mistral-7B-compressed.Q3_K_M.gguf b/Mistral-7B-compressed.Q3_K_M.gguf new file mode 100644 index 0000000..fc05b27 --- /dev/null +++ b/Mistral-7B-compressed.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dcb92f3b628c42fa806cb261a5b4f51a89ecd295e89b6d48a482196b163393d +size 3518987072 diff --git a/Mistral-7B-compressed.Q3_K_S.gguf b/Mistral-7B-compressed.Q3_K_S.gguf new file mode 100644 index 0000000..4118f47 --- /dev/null +++ b/Mistral-7B-compressed.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37d6cd3efb8d9ab7402566ed70fe996e3053e4446ffe25bed2a14a90db636c0a +size 3164568384 diff --git a/Mistral-7B-compressed.Q4_K_M.gguf b/Mistral-7B-compressed.Q4_K_M.gguf new file mode 100644 index 0000000..80ad1bc --- /dev/null +++ b/Mistral-7B-compressed.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62e3b9d0d5524e159b95c6003ae6b4eca419c93583369cac01ebcb9d4d9de69e +size 4368440128 diff --git a/Mistral-7B-compressed.Q4_K_S.gguf b/Mistral-7B-compressed.Q4_K_S.gguf new file mode 100644 index 0000000..e4e1998 --- /dev/null +++ b/Mistral-7B-compressed.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf806f7597df6be501f5b3d4d9cfc7bd04d78b76f2e621e926293a64624c25fe +size 4140374848 diff --git a/Mistral-7B-compressed.Q5_K_M.gguf b/Mistral-7B-compressed.Q5_K_M.gguf new file mode 100644 index 0000000..4877de9 --- /dev/null +++ b/Mistral-7B-compressed.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f90c571fafa1de1635dead66e45da476b8dcb70767dd21eff5cc38fb25d238a2 +size 5131410240 diff --git a/Mistral-7B-compressed.Q5_K_S.gguf b/Mistral-7B-compressed.Q5_K_S.gguf new file mode 100644 index 0000000..adb1c4e --- /dev/null +++ b/Mistral-7B-compressed.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4390072b918f650829fe6efeeb411c0d635d3ca2e7590f9e072214eff9143d34 +size 4997716800 diff --git a/Mistral-7B-compressed.Q6_K.gguf b/Mistral-7B-compressed.Q6_K.gguf new file mode 100644 index 0000000..cc641ca --- /dev/null +++ b/Mistral-7B-compressed.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7125a8fcec480ec727c6edbcc91c7b01ba16e3962fb1ea2b2049f46e798a719 +size 5942065984 diff --git a/Mistral-7B-compressed.Q8_0.gguf b/Mistral-7B-compressed.Q8_0.gguf new file mode 100644 index 0000000..f9614b2 --- /dev/null +++ b/Mistral-7B-compressed.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2ad27a22e3ae6cde5cddbac85b50ccbeeb52932881ff79b981eaef469816358 +size 7695858496 diff --git a/Mistral-7B-compressed.f16.gguf b/Mistral-7B-compressed.f16.gguf new file mode 100644 index 0000000..9d929cb --- /dev/null +++ b/Mistral-7B-compressed.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bd5ec5635c049100ab88f8316a4674543b2ac00e475be5cbfc0a572de49f60c +size 14484732736 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c097e21 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: fraQtl/Mistral-7B-optimized +language: +- en +library_name: transformers +license: other +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- fraqtl +- kv-cache-optimized +- inference +--- +## About + + + + + + + + + +static quants of https://huggingface.co/fraQtl/Mistral-7B-optimized + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Mistral-7B-compressed-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Mistral-7B-compressed-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-compressed-GGUF/resolve/main/Mistral-7B-compressed.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-compressed-GGUF/resolve/main/Mistral-7B-compressed.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-compressed-GGUF/resolve/main/Mistral-7B-compressed.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-compressed-GGUF/resolve/main/Mistral-7B-compressed.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-compressed-GGUF/resolve/main/Mistral-7B-compressed.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-compressed-GGUF/resolve/main/Mistral-7B-compressed.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-compressed-GGUF/resolve/main/Mistral-7B-compressed.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-compressed-GGUF/resolve/main/Mistral-7B-compressed.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-compressed-GGUF/resolve/main/Mistral-7B-compressed.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-compressed-GGUF/resolve/main/Mistral-7B-compressed.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-compressed-GGUF/resolve/main/Mistral-7B-compressed.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-compressed-GGUF/resolve/main/Mistral-7B-compressed.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. + +