commit 823ef986ec85edb784b415e442f0fd8bd2334881 Author: ModelHub XC Date: Fri Apr 10 22:18:03 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/mpt-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a4ea716 --- /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 +mpt-7b.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..0fa1551 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +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 + + + + + + +static quants of https://huggingface.co/mosaicml/mpt-7b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/mpt-7b-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/mpt-7b-GGUF/resolve/main/mpt-7b.Q2_K.gguf) | Q2_K | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-GGUF/resolve/main/mpt-7b.IQ3_XS.gguf) | IQ3_XS | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-GGUF/resolve/main/mpt-7b.IQ3_S.gguf) | IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-GGUF/resolve/main/mpt-7b.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-GGUF/resolve/main/mpt-7b.IQ3_M.gguf) | IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-GGUF/resolve/main/mpt-7b.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-GGUF/resolve/main/mpt-7b.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-GGUF/resolve/main/mpt-7b.Q4_K_S.gguf) | Q4_K_S | 3.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-GGUF/resolve/main/mpt-7b.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-GGUF/resolve/main/mpt-7b.Q4_K_M.gguf) | Q4_K_M | 4.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-GGUF/resolve/main/mpt-7b.Q5_K_S.gguf) | Q5_K_S | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-GGUF/resolve/main/mpt-7b.Q5_K_M.gguf) | Q5_K_M | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-GGUF/resolve/main/mpt-7b.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-GGUF/resolve/main/mpt-7b.Q8_0.gguf) | Q8_0 | 7.2 | 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. + + diff --git a/mpt-7b.IQ3_M.gguf b/mpt-7b.IQ3_M.gguf new file mode 100644 index 0000000..a1f00f4 --- /dev/null +++ b/mpt-7b.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a282e1407f23c53baa23eab5719fcad20681efd23828c33c4fe7584f332c4c3b +size 3261405216 diff --git a/mpt-7b.IQ3_S.gguf b/mpt-7b.IQ3_S.gguf new file mode 100644 index 0000000..f745461 --- /dev/null +++ b/mpt-7b.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bfac0e86bf59060f5c25b2c4705d9246c4e5aa64b60ffc2a3b7c27904f8808a +size 2940540960 diff --git a/mpt-7b.IQ3_XS.gguf b/mpt-7b.IQ3_XS.gguf new file mode 100644 index 0000000..ff9701d --- /dev/null +++ b/mpt-7b.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:308ca499c69101df61b2daee6143b799861002f676bc39d7a21c8dadb8e3fc88 +size 2865043488 diff --git a/mpt-7b.IQ4_XS.gguf b/mpt-7b.IQ4_XS.gguf new file mode 100644 index 0000000..a92dc9e --- /dev/null +++ b/mpt-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:726bd726172fa4e1c7e792462f519a71b95b7bbe96b5b161f1043a07787c5c01 +size 3636795424 diff --git a/mpt-7b.Q2_K.gguf b/mpt-7b.Q2_K.gguf new file mode 100644 index 0000000..1bdf42b --- /dev/null +++ b/mpt-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:263e71ebf05c3b40f8cf4d08976ba54ab6c9f615cdd8a39f9657d7ecf9c4ea2f +size 2558859296 diff --git a/mpt-7b.Q3_K_L.gguf b/mpt-7b.Q3_K_L.gguf new file mode 100644 index 0000000..bbfb899 --- /dev/null +++ b/mpt-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:691ce6c531011bea37ca6f10e48ef72e1f62ab959351c81fcf61493f03ad49fa +size 3846510624 diff --git a/mpt-7b.Q3_K_M.gguf b/mpt-7b.Q3_K_M.gguf new file mode 100644 index 0000000..8e8ae7a --- /dev/null +++ b/mpt-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be20639aa4d2ff7f892a0e46ccecb41049c8b9fbe99c75976d442ee4a9562b6d +size 3527743520 diff --git a/mpt-7b.Q3_K_S.gguf b/mpt-7b.Q3_K_S.gguf new file mode 100644 index 0000000..a05c61b --- /dev/null +++ b/mpt-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e02349f23a47f42aa6ae711b6fb7c7658a7fd585c88911f6c80ed5e90319caa5 +size 2940540960 diff --git a/mpt-7b.Q4_K_M.gguf b/mpt-7b.Q4_K_M.gguf new file mode 100644 index 0000000..e1466ef --- /dev/null +++ b/mpt-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e31e6fd45dd6a905e88d1721489e763cc0e934f8dfe3f5d3fbdadad5ddc3a058 +size 4274329632 diff --git a/mpt-7b.Q4_K_S.gguf b/mpt-7b.Q4_K_S.gguf new file mode 100644 index 0000000..430badb --- /dev/null +++ b/mpt-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ebb3e880c8aaea14e34c7ea67b86aa81ea70fa2ef73236b2ff36f74798a5529 +size 3829733408 diff --git a/mpt-7b.Q5_K_M.gguf b/mpt-7b.Q5_K_M.gguf new file mode 100644 index 0000000..2c81cd8 --- /dev/null +++ b/mpt-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6235f37c51e5451d87b9f2e5aace33d83a94aa4044129a9794eac9b54ad63e2f +size 4958001184 diff --git a/mpt-7b.Q5_K_S.gguf b/mpt-7b.Q5_K_S.gguf new file mode 100644 index 0000000..8b4faf2 --- /dev/null +++ b/mpt-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:197640a3fec3d1cb3398faae4ad6e966d21406c20adb77de367855105b839f6e +size 4601485344 diff --git a/mpt-7b.Q6_K.gguf b/mpt-7b.Q6_K.gguf new file mode 100644 index 0000000..519d1e2 --- /dev/null +++ b/mpt-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16e39179d70c586a3c43a26bb42b588da5e0cd37c246fe52df02632d276702fc +size 5457123360 diff --git a/mpt-7b.Q8_0.gguf b/mpt-7b.Q8_0.gguf new file mode 100644 index 0000000..f0061ca --- /dev/null +++ b/mpt-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7da93d338a3077ae7bce5a96fb60bd9dd2a378e544d9b9dfca259b82c7ca19e3 +size 7067432992