commit 87005ba7cb2fd0379ddf7cf91f49fbda3f68224f Author: ModelHub XC Date: Thu Sep 17 12:37:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Wukong-Mistral-7B-v0.3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2673eed --- /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 +Wukong-Mistral-7B-v0.3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Wukong-Mistral-7B-v0.3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Wukong-Mistral-7B-v0.3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Wukong-Mistral-7B-v0.3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Wukong-Mistral-7B-v0.3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Wukong-Mistral-7B-v0.3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Wukong-Mistral-7B-v0.3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Wukong-Mistral-7B-v0.3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Wukong-Mistral-7B-v0.3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Wukong-Mistral-7B-v0.3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Wukong-Mistral-7B-v0.3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Wukong-Mistral-7B-v0.3.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4e3f4c7 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: RESMPDEV/Wukong-Mistral-7B-v0.3 +datasets: +- cognitivecomputations/Dolphin-2.9 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/RESMPDEV/Wukong-Mistral-7B-v0.3 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Wukong-Mistral-7B-v0.3-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Wukong-Mistral-7B-v0.3-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/Wukong-Mistral-7B-v0.3-GGUF/resolve/main/Wukong-Mistral-7B-v0.3.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Wukong-Mistral-7B-v0.3-GGUF/resolve/main/Wukong-Mistral-7B-v0.3.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Wukong-Mistral-7B-v0.3-GGUF/resolve/main/Wukong-Mistral-7B-v0.3.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Wukong-Mistral-7B-v0.3-GGUF/resolve/main/Wukong-Mistral-7B-v0.3.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Wukong-Mistral-7B-v0.3-GGUF/resolve/main/Wukong-Mistral-7B-v0.3.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Wukong-Mistral-7B-v0.3-GGUF/resolve/main/Wukong-Mistral-7B-v0.3.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Wukong-Mistral-7B-v0.3-GGUF/resolve/main/Wukong-Mistral-7B-v0.3.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Wukong-Mistral-7B-v0.3-GGUF/resolve/main/Wukong-Mistral-7B-v0.3.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Wukong-Mistral-7B-v0.3-GGUF/resolve/main/Wukong-Mistral-7B-v0.3.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Wukong-Mistral-7B-v0.3-GGUF/resolve/main/Wukong-Mistral-7B-v0.3.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Wukong-Mistral-7B-v0.3-GGUF/resolve/main/Wukong-Mistral-7B-v0.3.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Wukong-Mistral-7B-v0.3-GGUF/resolve/main/Wukong-Mistral-7B-v0.3.f16.gguf) | f16 | 14.6 | 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/Wukong-Mistral-7B-v0.3.IQ4_XS.gguf b/Wukong-Mistral-7B-v0.3.IQ4_XS.gguf new file mode 100644 index 0000000..3f2f157 --- /dev/null +++ b/Wukong-Mistral-7B-v0.3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99299b7b3339c97c44f00400fad389c5f17b2f06ff53841d2ef87b5b2725df9c +size 3948674688 diff --git a/Wukong-Mistral-7B-v0.3.Q2_K.gguf b/Wukong-Mistral-7B-v0.3.Q2_K.gguf new file mode 100644 index 0000000..e1a36ff --- /dev/null +++ b/Wukong-Mistral-7B-v0.3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad45cfdf79955dfff8ff34633fb47249065d0e1d31d0cb6c012707e03553d0d1 +size 2722887680 diff --git a/Wukong-Mistral-7B-v0.3.Q3_K_L.gguf b/Wukong-Mistral-7B-v0.3.Q3_K_L.gguf new file mode 100644 index 0000000..c06ccbc --- /dev/null +++ b/Wukong-Mistral-7B-v0.3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c3c10cbc5b24229f7f841402f0c0865ab9f624bb972fe9f10e2238d826f4d98 +size 3825990464 diff --git a/Wukong-Mistral-7B-v0.3.Q3_K_M.gguf b/Wukong-Mistral-7B-v0.3.Q3_K_M.gguf new file mode 100644 index 0000000..85dff91 --- /dev/null +++ b/Wukong-Mistral-7B-v0.3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da14876591b37fb9f938587cf169ae092b2dde36c8d69a3262503c09d0c68813 +size 3522952000 diff --git a/Wukong-Mistral-7B-v0.3.Q3_K_S.gguf b/Wukong-Mistral-7B-v0.3.Q3_K_S.gguf new file mode 100644 index 0000000..1ec3126 --- /dev/null +++ b/Wukong-Mistral-7B-v0.3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc283b3c739a552bd8b4b74f6699e5f68f74b0785b47dae1d6926208d2c5a7a8 +size 3168533312 diff --git a/Wukong-Mistral-7B-v0.3.Q4_K_M.gguf b/Wukong-Mistral-7B-v0.3.Q4_K_M.gguf new file mode 100644 index 0000000..5894749 --- /dev/null +++ b/Wukong-Mistral-7B-v0.3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:773d916cebb802f3ec08d937a6bf2e51a8dd579d4d9e17d548798edead0c3822 +size 4372823936 diff --git a/Wukong-Mistral-7B-v0.3.Q4_K_S.gguf b/Wukong-Mistral-7B-v0.3.Q4_K_S.gguf new file mode 100644 index 0000000..79442ab --- /dev/null +++ b/Wukong-Mistral-7B-v0.3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:278d92be5d91e077928dcee860552d1288b22462bc32665df32d4ac6104ddf34 +size 4144758656 diff --git a/Wukong-Mistral-7B-v0.3.Q5_K_M.gguf b/Wukong-Mistral-7B-v0.3.Q5_K_M.gguf new file mode 100644 index 0000000..5d077ce --- /dev/null +++ b/Wukong-Mistral-7B-v0.3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9efaa315720bf88cb137ea4e4fdb0ea5911fde6348219d89681813a24343a229 +size 5136188288 diff --git a/Wukong-Mistral-7B-v0.3.Q5_K_S.gguf b/Wukong-Mistral-7B-v0.3.Q5_K_S.gguf new file mode 100644 index 0000000..15a3a87 --- /dev/null +++ b/Wukong-Mistral-7B-v0.3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:076cd6951962d44636c612d5982096d85339c6f4d27084a577ffe5aa5a953f98 +size 5002494848 diff --git a/Wukong-Mistral-7B-v0.3.Q6_K.gguf b/Wukong-Mistral-7B-v0.3.Q6_K.gguf new file mode 100644 index 0000000..31da36c --- /dev/null +++ b/Wukong-Mistral-7B-v0.3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21c423c92026586fc665deda053dfb92827ce4926936dcb0c46f77f4a2fe41c3 +size 5947262912 diff --git a/Wukong-Mistral-7B-v0.3.Q8_0.gguf b/Wukong-Mistral-7B-v0.3.Q8_0.gguf new file mode 100644 index 0000000..1ff7310 --- /dev/null +++ b/Wukong-Mistral-7B-v0.3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98b2a9a2e2616d285e9f7b083b2f334010c356cbff870af64142e73c572a4f74 +size 7702583104 diff --git a/Wukong-Mistral-7B-v0.3.f16.gguf b/Wukong-Mistral-7B-v0.3.f16.gguf new file mode 100644 index 0000000..bce52b7 --- /dev/null +++ b/Wukong-Mistral-7B-v0.3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1081a8c20d6d8895e45ea8205b294377aa73352f8c9606808845f9964837cf0c +size 14497370944