commit 32bb2d6c14265e0b613328f5c81eb915dab493a2 Author: ModelHub XC Date: Tue May 12 02:17:32 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/mpt-7b-8k-instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..db77a32 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,58 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +mpt-7b-8k-instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-8k-instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-8k-instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-8k-instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-8k-instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-8k-instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-8k-instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-8k-instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-8k-instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-8k-instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-8k-instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-8k-instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-8k-instruct.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-8k-instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-8k-instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-8k-instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-8k-instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-8k-instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-8k-instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-8k-instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-8k-instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-8k-instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..989780e --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +base_model: mosaicml/mpt-7b-8k-instruct +datasets: +- competition_math +- knkarthick/dialogsum +- mosaicml/dolly_hhrlhf +- duorc +- emozilla/quality +- scrolls/summ_screen_fd +- spider +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- Composer +- MosaicML +- llm-foundry +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/mosaicml/mpt-7b-8k-instruct + + +static quants are available at https://huggingface.co/mradermacher/mpt-7b-8k-instruct-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/mpt-7b-8k-instruct-i1-GGUF/resolve/main/mpt-7b-8k-instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 1.6 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-8k-instruct-i1-GGUF/resolve/main/mpt-7b-8k-instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 1.7 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-8k-instruct-i1-GGUF/resolve/main/mpt-7b-8k-instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-8k-instruct-i1-GGUF/resolve/main/mpt-7b-8k-instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-8k-instruct-i1-GGUF/resolve/main/mpt-7b-8k-instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-8k-instruct-i1-GGUF/resolve/main/mpt-7b-8k-instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-8k-instruct-i1-GGUF/resolve/main/mpt-7b-8k-instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-8k-instruct-i1-GGUF/resolve/main/mpt-7b-8k-instruct.i1-Q2_K.gguf) | i1-Q2_K | 2.7 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-8k-instruct-i1-GGUF/resolve/main/mpt-7b-8k-instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-8k-instruct-i1-GGUF/resolve/main/mpt-7b-8k-instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-8k-instruct-i1-GGUF/resolve/main/mpt-7b-8k-instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-8k-instruct-i1-GGUF/resolve/main/mpt-7b-8k-instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-8k-instruct-i1-GGUF/resolve/main/mpt-7b-8k-instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-8k-instruct-i1-GGUF/resolve/main/mpt-7b-8k-instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-8k-instruct-i1-GGUF/resolve/main/mpt-7b-8k-instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-8k-instruct-i1-GGUF/resolve/main/mpt-7b-8k-instruct.i1-Q4_0.gguf) | i1-Q4_0 | 3.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-8k-instruct-i1-GGUF/resolve/main/mpt-7b-8k-instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 3.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-8k-instruct-i1-GGUF/resolve/main/mpt-7b-8k-instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-8k-instruct-i1-GGUF/resolve/main/mpt-7b-8k-instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-8k-instruct-i1-GGUF/resolve/main/mpt-7b-8k-instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-8k-instruct-i1-GGUF/resolve/main/mpt-7b-8k-instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-8k-instruct-i1-GGUF/resolve/main/mpt-7b-8k-instruct.i1-Q6_K.gguf) | i1-Q6_K | 5.6 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..3fc07b1 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03ddd31734b162e683ed6304db4bf30def5ee4d26a7d7d6841e3bdc27e85dc98 +size 3674395 diff --git a/mpt-7b-8k-instruct.i1-IQ1_M.gguf b/mpt-7b-8k-instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..fa7ef74 --- /dev/null +++ b/mpt-7b-8k-instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b55cdb077ca35e4fe36672c452d0123963522972c4595ec6051518e74b504695 +size 1604484256 diff --git a/mpt-7b-8k-instruct.i1-IQ1_S.gguf b/mpt-7b-8k-instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..3663862 --- /dev/null +++ b/mpt-7b-8k-instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ced1d6b28cf36effd6d2c6b8e64d340986b420e64f53560ffd30a460f8a57fea +size 1472363680 diff --git a/mpt-7b-8k-instruct.i1-IQ2_M.gguf b/mpt-7b-8k-instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..7a19f9c --- /dev/null +++ b/mpt-7b-8k-instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65fac321558f323adbf0ad7eb1114c7f899d923424ba93d6880dbb326c5ec5d4 +size 2296544416 diff --git a/mpt-7b-8k-instruct.i1-IQ2_S.gguf b/mpt-7b-8k-instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..5aa9cdb --- /dev/null +++ b/mpt-7b-8k-instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b788ad9c9d239ce17946fe74a49d0afc845a828751e6857bdb4074f0484b931a +size 2120383648 diff --git a/mpt-7b-8k-instruct.i1-IQ2_XS.gguf b/mpt-7b-8k-instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..f0e8d65 --- /dev/null +++ b/mpt-7b-8k-instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5438a66eca068c8038281a7dab76360bc4b18661f6a44aed07fe3f031a831c39 +size 2017623200 diff --git a/mpt-7b-8k-instruct.i1-IQ2_XXS.gguf b/mpt-7b-8k-instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..4901005 --- /dev/null +++ b/mpt-7b-8k-instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a3839806b9ebe88c1f18ed4d5d45f8038550ac98c95d353ca4ab253d0a47be0 +size 1824685216 diff --git a/mpt-7b-8k-instruct.i1-IQ3_M.gguf b/mpt-7b-8k-instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..afc5031 --- /dev/null +++ b/mpt-7b-8k-instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99fc584e47566685aa35e42daa95fdc22aae7249a95f7634d2f3546f3b9c15e8 +size 3261406368 diff --git a/mpt-7b-8k-instruct.i1-IQ3_S.gguf b/mpt-7b-8k-instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..f77ce7a --- /dev/null +++ b/mpt-7b-8k-instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d265112cac2ee0617b56634b486a17a212d0a4a02c42a34fb506738a8092e9f7 +size 2940542112 diff --git a/mpt-7b-8k-instruct.i1-IQ3_XS.gguf b/mpt-7b-8k-instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..4087744 --- /dev/null +++ b/mpt-7b-8k-instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62d2bd2c8fc3d7e16f5c2a2d8a4917012c889e3e0c68e3cfddc90da4edf4b974 +size 2865044640 diff --git a/mpt-7b-8k-instruct.i1-IQ3_XXS.gguf b/mpt-7b-8k-instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..b0d215a --- /dev/null +++ b/mpt-7b-8k-instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15a541c32bec3fdd35f1100f43bbdb9be8f0d4ee7c72f33f143f6e907242ae88 +size 2636283040 diff --git a/mpt-7b-8k-instruct.i1-IQ4_XS.gguf b/mpt-7b-8k-instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..65e7449 --- /dev/null +++ b/mpt-7b-8k-instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f929541c315314a08f244e9819e572688be0a7733fb42a3b7ea3feedd109797 +size 3594853536 diff --git a/mpt-7b-8k-instruct.i1-Q2_K.gguf b/mpt-7b-8k-instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..e06ab72 --- /dev/null +++ b/mpt-7b-8k-instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c96164158350cb9c0e056fd2215b496a110aef8e0fe5e4b108b713a49e21d99c +size 2558860448 diff --git a/mpt-7b-8k-instruct.i1-Q2_K_S.gguf b/mpt-7b-8k-instruct.i1-Q2_K_S.gguf new file mode 100644 index 0000000..cc9de13 --- /dev/null +++ b/mpt-7b-8k-instruct.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7319ddb90073c6a13a1e8b5fbce8bc9d4af21beea6b1acbc0d121ee30248a092 +size 2349145248 diff --git a/mpt-7b-8k-instruct.i1-Q3_K_L.gguf b/mpt-7b-8k-instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..041eeca --- /dev/null +++ b/mpt-7b-8k-instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03c08a7a82556e75a4709977579c7de37abb18d498cda1fd1eacf44ebe8db876 +size 3846511776 diff --git a/mpt-7b-8k-instruct.i1-Q3_K_M.gguf b/mpt-7b-8k-instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..9cf2ee9 --- /dev/null +++ b/mpt-7b-8k-instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7287d9c7300ab44671bd20c545c81d2c032ebb96f5ac48a49e8df231d10bbda1 +size 3527744672 diff --git a/mpt-7b-8k-instruct.i1-Q3_K_S.gguf b/mpt-7b-8k-instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..ce98bff --- /dev/null +++ b/mpt-7b-8k-instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96708036f26902da250cba2faf9448e0108ac0021248d5fe9ac9c07bd8c947a7 +size 2940542112 diff --git a/mpt-7b-8k-instruct.i1-Q4_0.gguf b/mpt-7b-8k-instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..48eb905 --- /dev/null +++ b/mpt-7b-8k-instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fab363c1820b997caa1cd9817172bfbd8ef415f906cbaa5326e6a6ed36867910 +size 3812957344 diff --git a/mpt-7b-8k-instruct.i1-Q4_K_M.gguf b/mpt-7b-8k-instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..8cdbc16 --- /dev/null +++ b/mpt-7b-8k-instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80bbd880967f72aa5e23ed1e043d17e417b39910a88269a43ca2d7a04ec5eed4 +size 4274330784 diff --git a/mpt-7b-8k-instruct.i1-Q4_K_S.gguf b/mpt-7b-8k-instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..3646578 --- /dev/null +++ b/mpt-7b-8k-instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87346195fae86d9122bad787e1e65880cb7c2759fe18a25e3252d4c365da4be7 +size 3829734560 diff --git a/mpt-7b-8k-instruct.i1-Q5_K_M.gguf b/mpt-7b-8k-instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..4741eb5 --- /dev/null +++ b/mpt-7b-8k-instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b88681b09d377a9c7ad6eb7f35b6377906bd032e6e0e9a19915c61e2e8c8585 +size 4958002336 diff --git a/mpt-7b-8k-instruct.i1-Q5_K_S.gguf b/mpt-7b-8k-instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..555ded5 --- /dev/null +++ b/mpt-7b-8k-instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:935c8fedbd7e097ddc52bd5a94ac80578b0b12bfb90a5ada2974012417f7d2e5 +size 4601486496 diff --git a/mpt-7b-8k-instruct.i1-Q6_K.gguf b/mpt-7b-8k-instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..ad57af0 --- /dev/null +++ b/mpt-7b-8k-instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c63c6e6238758fe562d4040aa49be88d73064dabcfe48688821efb28051f90a +size 5457124512