commit 7b63837f935ed3313d68f160db6de1441d23031a Author: ModelHub XC Date: Mon Apr 13 03:16:55 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/mpt-7b-wizardlm-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a05e945 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-wizardlm.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-wizardlm.f16.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-wizardlm.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-wizardlm.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-wizardlm.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-wizardlm.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-wizardlm.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-wizardlm.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-wizardlm.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-wizardlm.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-wizardlm.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-wizardlm.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-wizardlm.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-wizardlm.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +mpt-7b-wizardlm.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..62ad230 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: hugging2021/mpt-7b-wizardlm +datasets: +- ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/hugging2021/mpt-7b-wizardlm + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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-wizardlm-GGUF/resolve/main/mpt-7b-wizardlm.Q2_K.gguf) | Q2_K | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-wizardlm-GGUF/resolve/main/mpt-7b-wizardlm.IQ3_XS.gguf) | IQ3_XS | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-wizardlm-GGUF/resolve/main/mpt-7b-wizardlm.IQ3_S.gguf) | IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-wizardlm-GGUF/resolve/main/mpt-7b-wizardlm.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-wizardlm-GGUF/resolve/main/mpt-7b-wizardlm.IQ3_M.gguf) | IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-wizardlm-GGUF/resolve/main/mpt-7b-wizardlm.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-wizardlm-GGUF/resolve/main/mpt-7b-wizardlm.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-wizardlm-GGUF/resolve/main/mpt-7b-wizardlm.Q4_K_S.gguf) | Q4_K_S | 3.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-wizardlm-GGUF/resolve/main/mpt-7b-wizardlm.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-wizardlm-GGUF/resolve/main/mpt-7b-wizardlm.Q4_K_M.gguf) | Q4_K_M | 4.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-wizardlm-GGUF/resolve/main/mpt-7b-wizardlm.Q5_K_S.gguf) | Q5_K_S | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-wizardlm-GGUF/resolve/main/mpt-7b-wizardlm.Q5_K_M.gguf) | Q5_K_M | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-wizardlm-GGUF/resolve/main/mpt-7b-wizardlm.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-wizardlm-GGUF/resolve/main/mpt-7b-wizardlm.Q8_0.gguf) | Q8_0 | 7.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/mpt-7b-wizardlm-GGUF/resolve/main/mpt-7b-wizardlm.f16.gguf) | f16 | 13.4 | 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. + + diff --git a/mpt-7b-wizardlm.IQ3_M.gguf b/mpt-7b-wizardlm.IQ3_M.gguf new file mode 100644 index 0000000..0cf3bef --- /dev/null +++ b/mpt-7b-wizardlm.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:188da056a5c10a3cd6c9690848495f243ceb782308c955d9cdd6ab0a9c8ca3e8 +size 3261404832 diff --git a/mpt-7b-wizardlm.IQ3_S.gguf b/mpt-7b-wizardlm.IQ3_S.gguf new file mode 100644 index 0000000..3eb768d --- /dev/null +++ b/mpt-7b-wizardlm.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9979195b9ac28a655be6ae6275a4dbc1f0fd8736a98d6a1c525701e71984242 +size 2940540576 diff --git a/mpt-7b-wizardlm.IQ3_XS.gguf b/mpt-7b-wizardlm.IQ3_XS.gguf new file mode 100644 index 0000000..76fe4f2 --- /dev/null +++ b/mpt-7b-wizardlm.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ff3e884f78bb8c0d3bf6afc9d3eca10b26951c304d3079c6d26094d2fed888f +size 2865043104 diff --git a/mpt-7b-wizardlm.IQ4_XS.gguf b/mpt-7b-wizardlm.IQ4_XS.gguf new file mode 100644 index 0000000..02fcf76 --- /dev/null +++ b/mpt-7b-wizardlm.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0b24e4a87fc1c2b18b45f7f3817874edb14761150806f16f45ff411d0862adb +size 3636795040 diff --git a/mpt-7b-wizardlm.Q2_K.gguf b/mpt-7b-wizardlm.Q2_K.gguf new file mode 100644 index 0000000..cf3742d --- /dev/null +++ b/mpt-7b-wizardlm.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:570582122d271a58acd1e423585ce96e3e16e3e57e117dffb12203bdbaf5466a +size 2558858912 diff --git a/mpt-7b-wizardlm.Q3_K_L.gguf b/mpt-7b-wizardlm.Q3_K_L.gguf new file mode 100644 index 0000000..7de74e5 --- /dev/null +++ b/mpt-7b-wizardlm.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57ec7160d45544960a7a86e903af2642d64e211a972816f996c657cb6fd20f6a +size 3846510240 diff --git a/mpt-7b-wizardlm.Q3_K_M.gguf b/mpt-7b-wizardlm.Q3_K_M.gguf new file mode 100644 index 0000000..ed90caa --- /dev/null +++ b/mpt-7b-wizardlm.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2ddb64cb763642ae740dd052e34fa333f7bc01e63571d8571bcc1a59ef35001 +size 3527743136 diff --git a/mpt-7b-wizardlm.Q3_K_S.gguf b/mpt-7b-wizardlm.Q3_K_S.gguf new file mode 100644 index 0000000..2a00760 --- /dev/null +++ b/mpt-7b-wizardlm.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32ef68235a216b3cd4d03c9c95e40018bf91dbfc2f4659e22874ef95009a8619 +size 2940540576 diff --git a/mpt-7b-wizardlm.Q4_K_M.gguf b/mpt-7b-wizardlm.Q4_K_M.gguf new file mode 100644 index 0000000..4d52c62 --- /dev/null +++ b/mpt-7b-wizardlm.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f5a81c8159d237d31995765dffe4f86db3a80cd68cff95ad5abfd91b58282f1 +size 4274329248 diff --git a/mpt-7b-wizardlm.Q4_K_S.gguf b/mpt-7b-wizardlm.Q4_K_S.gguf new file mode 100644 index 0000000..fc07a25 --- /dev/null +++ b/mpt-7b-wizardlm.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63472ff28c7568d2e8cc3fb18f5894e0f22b395e64e83852469a622617d73147 +size 3829733024 diff --git a/mpt-7b-wizardlm.Q5_K_M.gguf b/mpt-7b-wizardlm.Q5_K_M.gguf new file mode 100644 index 0000000..b553b59 --- /dev/null +++ b/mpt-7b-wizardlm.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e276c1e4df8505e4095dc4e4fa8aaedec83231db88c19bb9099ea3b2eb5449a9 +size 4958000800 diff --git a/mpt-7b-wizardlm.Q5_K_S.gguf b/mpt-7b-wizardlm.Q5_K_S.gguf new file mode 100644 index 0000000..cf7bd9c --- /dev/null +++ b/mpt-7b-wizardlm.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ece86bb95e81da715b976ed0a92908b8ead5ab2f09a0d7f3a2589bd73ef543bd +size 4601484960 diff --git a/mpt-7b-wizardlm.Q6_K.gguf b/mpt-7b-wizardlm.Q6_K.gguf new file mode 100644 index 0000000..f20c1cc --- /dev/null +++ b/mpt-7b-wizardlm.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8f419aa3e7f099ffdd479d8bba2a12192c027fbb915f48dda316b5586eb0319 +size 5457122976 diff --git a/mpt-7b-wizardlm.Q8_0.gguf b/mpt-7b-wizardlm.Q8_0.gguf new file mode 100644 index 0000000..275b56d --- /dev/null +++ b/mpt-7b-wizardlm.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad20bc0c415e69523ebe9f9f1ba1a9c6f4e56181cfc000449d43b9630ae63c92 +size 7067432608 diff --git a/mpt-7b-wizardlm.f16.gguf b/mpt-7b-wizardlm.f16.gguf new file mode 100644 index 0000000..b00c4a9 --- /dev/null +++ b/mpt-7b-wizardlm.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b667f7a461191b044d352d383d4a071eaffeeee5c8071c0cab8e0f18fe7f56ac +size 13300889248