commit 33b6af3eaec208a9155d2705f2c5d84faf277768 Author: ModelHub XC Date: Sat May 23 01:42:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/mpt-7b-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c4fbe36 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..ed2346a --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: mosaicml/mpt-7b +datasets: +- mc4 +- c4 +- togethercomputer/RedPajama-Data-1T +- bigcode/the-stack +- allenai/s2orc +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- Composer +- MosaicML +- llm-foundry +- StreamingDatasets +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/mosaicml/mpt-7b + + +static quants are available at https://huggingface.co/mradermacher/mpt-7b-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-i1-GGUF/resolve/main/mpt-7b.i1-IQ1_S.gguf) | i1-IQ1_S | 1.6 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-i1-GGUF/resolve/main/mpt-7b.i1-IQ1_M.gguf) | i1-IQ1_M | 1.7 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-i1-GGUF/resolve/main/mpt-7b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-i1-GGUF/resolve/main/mpt-7b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-i1-GGUF/resolve/main/mpt-7b.i1-IQ2_S.gguf) | i1-IQ2_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-i1-GGUF/resolve/main/mpt-7b.i1-IQ2_M.gguf) | i1-IQ2_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-i1-GGUF/resolve/main/mpt-7b.i1-Q2_K.gguf) | i1-Q2_K | 2.7 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-i1-GGUF/resolve/main/mpt-7b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-i1-GGUF/resolve/main/mpt-7b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-i1-GGUF/resolve/main/mpt-7b.i1-IQ3_S.gguf) | i1-IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-i1-GGUF/resolve/main/mpt-7b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-i1-GGUF/resolve/main/mpt-7b.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-i1-GGUF/resolve/main/mpt-7b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-i1-GGUF/resolve/main/mpt-7b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-i1-GGUF/resolve/main/mpt-7b.i1-Q4_0.gguf) | i1-Q4_0 | 3.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-i1-GGUF/resolve/main/mpt-7b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 3.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-i1-GGUF/resolve/main/mpt-7b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-i1-GGUF/resolve/main/mpt-7b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-i1-GGUF/resolve/main/mpt-7b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-i1-GGUF/resolve/main/mpt-7b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-i1-GGUF/resolve/main/mpt-7b.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..a35db05 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e357256f50a2c8b75cdb389ac495578645747aa874e2dccb599bd96dd54e958f +size 3674395 diff --git a/mpt-7b.i1-IQ1_M.gguf b/mpt-7b.i1-IQ1_M.gguf new file mode 100644 index 0000000..977322c --- /dev/null +++ b/mpt-7b.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ee6a41bff25574ee61086edd3347092a22a1b079dbe7620614a3f7297fb1b44 +size 1604483328 diff --git a/mpt-7b.i1-IQ1_S.gguf b/mpt-7b.i1-IQ1_S.gguf new file mode 100644 index 0000000..e0f429d --- /dev/null +++ b/mpt-7b.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f00de6dd1381a5f2c2e0d7cc0995290648f9ad0b9b8a5a7362a24e7f39d7634a +size 1472362752 diff --git a/mpt-7b.i1-IQ2_M.gguf b/mpt-7b.i1-IQ2_M.gguf new file mode 100644 index 0000000..a226623 --- /dev/null +++ b/mpt-7b.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ae68ade8af905f31feb1766e5171cf836e36079a453b881af3fb5f4c9b8df7f +size 2296543488 diff --git a/mpt-7b.i1-IQ2_S.gguf b/mpt-7b.i1-IQ2_S.gguf new file mode 100644 index 0000000..b4c6e27 --- /dev/null +++ b/mpt-7b.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03fcec365176ced9501539d606a310cb749e2ae186a3ea378bc36b69c4777085 +size 2120382720 diff --git a/mpt-7b.i1-IQ2_XS.gguf b/mpt-7b.i1-IQ2_XS.gguf new file mode 100644 index 0000000..ab0d235 --- /dev/null +++ b/mpt-7b.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:488a10692396ca20e9bdb02dccd5eb5559eb491c041f00f64f2c50995d44d82f +size 2017622272 diff --git a/mpt-7b.i1-IQ2_XXS.gguf b/mpt-7b.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..2654ecb --- /dev/null +++ b/mpt-7b.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd2ab4e806b27445fbf2cc37fd86ec32864c9fb10571101b9bdf4e67eaa0bc62 +size 1824684288 diff --git a/mpt-7b.i1-IQ3_M.gguf b/mpt-7b.i1-IQ3_M.gguf new file mode 100644 index 0000000..e219deb --- /dev/null +++ b/mpt-7b.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c99a5f67fff852ec20b2a76a807ed5b9e4a20e43f1c08205f21750d9f8452164 +size 3261405440 diff --git a/mpt-7b.i1-IQ3_S.gguf b/mpt-7b.i1-IQ3_S.gguf new file mode 100644 index 0000000..ff697f3 --- /dev/null +++ b/mpt-7b.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72653deb7928873a5fe48493fc3a4aa2891f27179dc626dd53f518f807df442f +size 2940541184 diff --git a/mpt-7b.i1-IQ3_XS.gguf b/mpt-7b.i1-IQ3_XS.gguf new file mode 100644 index 0000000..7aa9a2a --- /dev/null +++ b/mpt-7b.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd793cc3e3ac6a9022627debb542425288d69db9fd50a0cb8b2126d68854710f +size 2865043712 diff --git a/mpt-7b.i1-IQ3_XXS.gguf b/mpt-7b.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..17d6934 --- /dev/null +++ b/mpt-7b.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8dcea2246cdcbd77c7ae415e5a1fe998af5763540cb6c832b7baaf8d7ab8b9f +size 2636282112 diff --git a/mpt-7b.i1-IQ4_XS.gguf b/mpt-7b.i1-IQ4_XS.gguf new file mode 100644 index 0000000..e22ce35 --- /dev/null +++ b/mpt-7b.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f44df8c0db69532dead4d3829d163346d7911c8459b14302a0d73cf87ce09e7 +size 3594852608 diff --git a/mpt-7b.i1-Q2_K.gguf b/mpt-7b.i1-Q2_K.gguf new file mode 100644 index 0000000..98cad4d --- /dev/null +++ b/mpt-7b.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48d6da5aadeb62e7ec91159021d95232795f05c4ad681573acdcc0fc948d8049 +size 2558859520 diff --git a/mpt-7b.i1-Q3_K_L.gguf b/mpt-7b.i1-Q3_K_L.gguf new file mode 100644 index 0000000..f2aa624 --- /dev/null +++ b/mpt-7b.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36ffc8098c0fc701d7727ac9c8c03718d5bd7dfb8e0f2be98c4b9bcd784cf2e2 +size 3846510848 diff --git a/mpt-7b.i1-Q3_K_M.gguf b/mpt-7b.i1-Q3_K_M.gguf new file mode 100644 index 0000000..c209ce8 --- /dev/null +++ b/mpt-7b.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efa8b111688bc2e57c91d80b9df283ce16de18f09ec5a654934a7a794b2e599c +size 3527743744 diff --git a/mpt-7b.i1-Q3_K_S.gguf b/mpt-7b.i1-Q3_K_S.gguf new file mode 100644 index 0000000..0014929 --- /dev/null +++ b/mpt-7b.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e2b2f2a087b486fb6262e7dbee74d46db1b9ec4406e853cc24d9f1cdace1530 +size 2940541184 diff --git a/mpt-7b.i1-Q4_0.gguf b/mpt-7b.i1-Q4_0.gguf new file mode 100644 index 0000000..931c7d9 --- /dev/null +++ b/mpt-7b.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b999dc9312c68ddaf9849dddeb43e41e38515383d29a0d957fe2469993975387 +size 3812956416 diff --git a/mpt-7b.i1-Q4_K_M.gguf b/mpt-7b.i1-Q4_K_M.gguf new file mode 100644 index 0000000..8a00ace --- /dev/null +++ b/mpt-7b.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d2ad02af9322022a6b96da8049e1eefed586b04cf8fb57c9bacc8e83e121cb3 +size 4274329856 diff --git a/mpt-7b.i1-Q4_K_S.gguf b/mpt-7b.i1-Q4_K_S.gguf new file mode 100644 index 0000000..66a90f6 --- /dev/null +++ b/mpt-7b.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c889eeb77f657ae7716f919b23bd6a2ee180d29f6743d9c0e0bc2bd7083537c6 +size 3829733632 diff --git a/mpt-7b.i1-Q5_K_M.gguf b/mpt-7b.i1-Q5_K_M.gguf new file mode 100644 index 0000000..6b9ca08 --- /dev/null +++ b/mpt-7b.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90bcfbcb33aedb7411b647ed389f99232cc9b010ace690e1f5d28a739fb662db +size 4958001408 diff --git a/mpt-7b.i1-Q5_K_S.gguf b/mpt-7b.i1-Q5_K_S.gguf new file mode 100644 index 0000000..c54b5df --- /dev/null +++ b/mpt-7b.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:353a43a4ff9f24738693a8fc8562afb5cd589b4c4a01c4d0d8710991c265807b +size 4601485568 diff --git a/mpt-7b.i1-Q6_K.gguf b/mpt-7b.i1-Q6_K.gguf new file mode 100644 index 0000000..3b2057b --- /dev/null +++ b/mpt-7b.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf3ee8489556b824713ba18a22716628ea387fc8b552a53dd0142f2ae6f672c9 +size 5457123584