commit e208ae2884f27c1921523b4af26437ee572927a6 Author: ModelHub XC Date: Sun Jun 14 21:53:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Viel-Mistral-v3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8c6a67f --- /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 +Viel-Mistral-v3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Viel-Mistral-v3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Viel-Mistral-v3.f16.gguf filter=lfs diff=lfs merge=lfs -text +Viel-Mistral-v3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Viel-Mistral-v3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Viel-Mistral-v3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Viel-Mistral-v3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Viel-Mistral-v3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Viel-Mistral-v3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Viel-Mistral-v3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Viel-Mistral-v3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Viel-Mistral-v3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..019b85e --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: ArsParadox/Viel-Mistral-v3 +datasets: +- ArsParadox/Viel_Dataset_Lite +language: +- en +library_name: transformers +license: gpl-3.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- rp +--- +## About + + + + + + +static quants of https://huggingface.co/ArsParadox/Viel-Mistral-v3 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Viel-Mistral-v3-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Viel-Mistral-v3-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/Viel-Mistral-v3-GGUF/resolve/main/Viel-Mistral-v3.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Viel-Mistral-v3-GGUF/resolve/main/Viel-Mistral-v3.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Viel-Mistral-v3-GGUF/resolve/main/Viel-Mistral-v3.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Viel-Mistral-v3-GGUF/resolve/main/Viel-Mistral-v3.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Viel-Mistral-v3-GGUF/resolve/main/Viel-Mistral-v3.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Viel-Mistral-v3-GGUF/resolve/main/Viel-Mistral-v3.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Viel-Mistral-v3-GGUF/resolve/main/Viel-Mistral-v3.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Viel-Mistral-v3-GGUF/resolve/main/Viel-Mistral-v3.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Viel-Mistral-v3-GGUF/resolve/main/Viel-Mistral-v3.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Viel-Mistral-v3-GGUF/resolve/main/Viel-Mistral-v3.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Viel-Mistral-v3-GGUF/resolve/main/Viel-Mistral-v3.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Viel-Mistral-v3-GGUF/resolve/main/Viel-Mistral-v3.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/Viel-Mistral-v3.IQ4_XS.gguf b/Viel-Mistral-v3.IQ4_XS.gguf new file mode 100644 index 0000000..db65f97 --- /dev/null +++ b/Viel-Mistral-v3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fad362f04b0dabe839aaf56d894de0c7dce9b93aba695ac7fff1fccaec65d1dd +size 3948664640 diff --git a/Viel-Mistral-v3.Q2_K.gguf b/Viel-Mistral-v3.Q2_K.gguf new file mode 100644 index 0000000..b8b3752 --- /dev/null +++ b/Viel-Mistral-v3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3f454f7fe14931b3afdfd205a9415db02b5f4894b2559ac779a410747f9d21e +size 2722879296 diff --git a/Viel-Mistral-v3.Q3_K_L.gguf b/Viel-Mistral-v3.Q3_K_L.gguf new file mode 100644 index 0000000..3b3e2ad --- /dev/null +++ b/Viel-Mistral-v3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c225cd2baacab20a5c18b0772db82d7134ce2ec9cc44b2077802e29f1af22f5 +size 3825981248 diff --git a/Viel-Mistral-v3.Q3_K_M.gguf b/Viel-Mistral-v3.Q3_K_M.gguf new file mode 100644 index 0000000..cf3b3af --- /dev/null +++ b/Viel-Mistral-v3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73705c8ae7820b0fd9896f4e9cf1e6b7642022f122b37f9f143447f2d03b289d +size 3522942784 diff --git a/Viel-Mistral-v3.Q3_K_S.gguf b/Viel-Mistral-v3.Q3_K_S.gguf new file mode 100644 index 0000000..057b077 --- /dev/null +++ b/Viel-Mistral-v3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96fb5417ab4e3f205d9daf6c719b74efa584fca3210e64cfd24070095f4d2ffa +size 3168524096 diff --git a/Viel-Mistral-v3.Q4_K_M.gguf b/Viel-Mistral-v3.Q4_K_M.gguf new file mode 100644 index 0000000..4417e9c --- /dev/null +++ b/Viel-Mistral-v3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55703750f887f18e2bad4368b1169c049c33f5e2236547fa566689d2fb5b699d +size 4372813632 diff --git a/Viel-Mistral-v3.Q4_K_S.gguf b/Viel-Mistral-v3.Q4_K_S.gguf new file mode 100644 index 0000000..60e9bd8 --- /dev/null +++ b/Viel-Mistral-v3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28138f57102f16df457482833b67489bea281ca1854a1d5b3acb3807d032f8df +size 4144748352 diff --git a/Viel-Mistral-v3.Q5_K_M.gguf b/Viel-Mistral-v3.Q5_K_M.gguf new file mode 100644 index 0000000..1a04f40 --- /dev/null +++ b/Viel-Mistral-v3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a5251e6e4beb535028d78ca2bb5f2479cdb209a63bd1ab7ed906f299c8cbc14 +size 5136176960 diff --git a/Viel-Mistral-v3.Q5_K_S.gguf b/Viel-Mistral-v3.Q5_K_S.gguf new file mode 100644 index 0000000..169a0b8 --- /dev/null +++ b/Viel-Mistral-v3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc07388ae3aa3b9adbe5742ddd5fddb5adcd3cdb235a96c41954791c09f6ebd0 +size 5002483520 diff --git a/Viel-Mistral-v3.Q6_K.gguf b/Viel-Mistral-v3.Q6_K.gguf new file mode 100644 index 0000000..e688b6f --- /dev/null +++ b/Viel-Mistral-v3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32bae302d04986d243fc8a382f43bd0308caf9be3b7888483819583fe7e5b971 +size 5947250496 diff --git a/Viel-Mistral-v3.Q8_0.gguf b/Viel-Mistral-v3.Q8_0.gguf new file mode 100644 index 0000000..ce29e71 --- /dev/null +++ b/Viel-Mistral-v3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92d7a4713a0420b6bfdcbf6b5fbc1423316d426f47b3379b423695a0c2fa5fbe +size 7702566720 diff --git a/Viel-Mistral-v3.f16.gguf b/Viel-Mistral-v3.f16.gguf new file mode 100644 index 0000000..26e00a4 --- /dev/null +++ b/Viel-Mistral-v3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eca98068b72b56fa75520c9a23cf35ed6229a630c5876b4d0f2e1e025dbf663e +size 14497339200