commit ef51da842cfebbb30d42a9026c56b041a9e3511c Author: ModelHub XC Date: Tue May 26 09:10:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Moxin-7B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..43bffd6 --- /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 +Moxin-7B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Moxin-7B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Moxin-7B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Moxin-7B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Moxin-7B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Moxin-7B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Moxin-7B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Moxin-7B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Moxin-7B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Moxin-7B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Moxin-7B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Moxin-7B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Moxin-7B-Instruct.IQ4_XS.gguf b/Moxin-7B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..724ee69 --- /dev/null +++ b/Moxin-7B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f97c2b72cf78ae7b76adc1178e40361885035645d8913b73d34f20a9e5b5bb4 +size 4410659424 diff --git a/Moxin-7B-Instruct.Q2_K.gguf b/Moxin-7B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..da87fd8 --- /dev/null +++ b/Moxin-7B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d6a7bfc1a12980dd915d3fe97d4f9a193d85a6191b882de7b96418545da5fee +size 3040278624 diff --git a/Moxin-7B-Instruct.Q3_K_L.gguf b/Moxin-7B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..30034ee --- /dev/null +++ b/Moxin-7B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1125677f856831f3c13f7f455e362a0572c0ccbc2858cf47335fea08c2b2c242 +size 4279248224 diff --git a/Moxin-7B-Instruct.Q3_K_M.gguf b/Moxin-7B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..ced13ee --- /dev/null +++ b/Moxin-7B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:450c0591c0a9f9e1d3211458a9e2d863d5450044c23d23200a601b0139b5d3d6 +size 3936363872 diff --git a/Moxin-7B-Instruct.Q3_K_S.gguf b/Moxin-7B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..b1eb370 --- /dev/null +++ b/Moxin-7B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16b9a1cc8f8422da69e2ab7b423945b8cd540f4961d6c38a3d29e71bb5b37f60 +size 3539608928 diff --git a/Moxin-7B-Instruct.Q4_K_M.gguf b/Moxin-7B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..0db660c --- /dev/null +++ b/Moxin-7B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3be2afa15b40428e864dcb7bd26add3b8ed9b6c34797a0242bf872452aa907f +size 4891792992 diff --git a/Moxin-7B-Instruct.Q4_K_S.gguf b/Moxin-7B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..a113b47 --- /dev/null +++ b/Moxin-7B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ce55b254301c60538a92f8b0710029d97f67c2ffbcc2e0a3e105a86057cb8af +size 4631287392 diff --git a/Moxin-7B-Instruct.Q5_K_M.gguf b/Moxin-7B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..fbadc75 --- /dev/null +++ b/Moxin-7B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0e885d1e0a99d9c563a91554675fff0570a71629ae3e7ec0d4d8c6f316c46c8 +size 5748090464 diff --git a/Moxin-7B-Instruct.Q5_K_S.gguf b/Moxin-7B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..08915ba --- /dev/null +++ b/Moxin-7B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f352677c3b7f98b84cc4aa82ffad922d59cca8a02d9cd0b2344cca716c0ba00d +size 5597685344 diff --git a/Moxin-7B-Instruct.Q6_K.gguf b/Moxin-7B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..c98fa38 --- /dev/null +++ b/Moxin-7B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8db60bcd6e220bd55a26c0edfd8f2ee58473bb05f253f73c4cf7e8a9f43d9253 +size 6657906528 diff --git a/Moxin-7B-Instruct.Q8_0.gguf b/Moxin-7B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..e08093b --- /dev/null +++ b/Moxin-7B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0d78208da0147331367da71e0ac2a883fda8ff46a998beb2fc9d5d29df2a388 +size 8623002976 diff --git a/Moxin-7B-Instruct.f16.gguf b/Moxin-7B-Instruct.f16.gguf new file mode 100644 index 0000000..168d851 --- /dev/null +++ b/Moxin-7B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d4a2c1c524fe94b6d40a0b866ac9be8a8ebdebf399abce1121e5f9d815cdf17 +size 16229827936 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d18f68f --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: moxin-org/Moxin-7B-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/moxin-org/Moxin-7B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Moxin-7B-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Moxin-7B-Instruct-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/Moxin-7B-Instruct-GGUF/resolve/main/Moxin-7B-Instruct.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Moxin-7B-Instruct-GGUF/resolve/main/Moxin-7B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Moxin-7B-Instruct-GGUF/resolve/main/Moxin-7B-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Moxin-7B-Instruct-GGUF/resolve/main/Moxin-7B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Moxin-7B-Instruct-GGUF/resolve/main/Moxin-7B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Moxin-7B-Instruct-GGUF/resolve/main/Moxin-7B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Moxin-7B-Instruct-GGUF/resolve/main/Moxin-7B-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Moxin-7B-Instruct-GGUF/resolve/main/Moxin-7B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Moxin-7B-Instruct-GGUF/resolve/main/Moxin-7B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Moxin-7B-Instruct-GGUF/resolve/main/Moxin-7B-Instruct.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Moxin-7B-Instruct-GGUF/resolve/main/Moxin-7B-Instruct.Q8_0.gguf) | Q8_0 | 8.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Moxin-7B-Instruct-GGUF/resolve/main/Moxin-7B-Instruct.f16.gguf) | f16 | 16.3 | 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. + +