commit c001d5450ec8665c5bdeb58ded2291416d8984d6 Author: ModelHub XC Date: Wed Jun 3 21:46:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Minmax-TOFU-2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1c17a31 --- /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 +Minmax-TOFU-2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Minmax-TOFU-2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Minmax-TOFU-2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Minmax-TOFU-2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Minmax-TOFU-2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Minmax-TOFU-2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Minmax-TOFU-2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Minmax-TOFU-2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Minmax-TOFU-2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Minmax-TOFU-2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Minmax-TOFU-2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Minmax-TOFU-2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Minmax-TOFU-2.IQ4_XS.gguf b/Minmax-TOFU-2.IQ4_XS.gguf new file mode 100644 index 0000000..71415bf --- /dev/null +++ b/Minmax-TOFU-2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d6edc5d741f1872baa0a15eb1c0bbca63a7c29931e6190c24c561b3f97c295c +size 748384544 diff --git a/Minmax-TOFU-2.Q2_K.gguf b/Minmax-TOFU-2.Q2_K.gguf new file mode 100644 index 0000000..b5ad3a7 --- /dev/null +++ b/Minmax-TOFU-2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59c37bc9dab6ee1c2448ce1cf304d96be85322ce6342dd100ee5c9cb96316336 +size 580874528 diff --git a/Minmax-TOFU-2.Q3_K_L.gguf b/Minmax-TOFU-2.Q3_K_L.gguf new file mode 100644 index 0000000..77ddf8c --- /dev/null +++ b/Minmax-TOFU-2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9703072fd5b40bf6407caf1cb0ecd4c2232ef72695c137464215ccc83e471518 +size 732524832 diff --git a/Minmax-TOFU-2.Q3_K_M.gguf b/Minmax-TOFU-2.Q3_K_M.gguf new file mode 100644 index 0000000..177b775 --- /dev/null +++ b/Minmax-TOFU-2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0835904578c7a9d2e3f01b9c613f6a1ef445c3a776c172a3fe4b1677ed3dfd0a +size 690843936 diff --git a/Minmax-TOFU-2.Q3_K_S.gguf b/Minmax-TOFU-2.Q3_K_S.gguf new file mode 100644 index 0000000..8c911c7 --- /dev/null +++ b/Minmax-TOFU-2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:772af9aac6089eda296291286732b690a8ce9f385e77e6f045aa8883bca7d199 +size 641691936 diff --git a/Minmax-TOFU-2.Q4_K_M.gguf b/Minmax-TOFU-2.Q4_K_M.gguf new file mode 100644 index 0000000..85d2336 --- /dev/null +++ b/Minmax-TOFU-2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c145f353c81a34ec2d5efbbd40db5eb187b97b7193133723cee85c85741b439d +size 807694624 diff --git a/Minmax-TOFU-2.Q4_K_S.gguf b/Minmax-TOFU-2.Q4_K_S.gguf new file mode 100644 index 0000000..4163eb5 --- /dev/null +++ b/Minmax-TOFU-2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8735463b56cfd39aff9ba6faee3eb0eca7aa18b2f776ba71465c1615b2def41c +size 775647520 diff --git a/Minmax-TOFU-2.Q5_K_M.gguf b/Minmax-TOFU-2.Q5_K_M.gguf new file mode 100644 index 0000000..e27f2af --- /dev/null +++ b/Minmax-TOFU-2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:094072bd235b82fa282101e5c7d48cc8fb56b09f0d0f3b82f4875a43be55f039 +size 911503648 diff --git a/Minmax-TOFU-2.Q5_K_S.gguf b/Minmax-TOFU-2.Q5_K_S.gguf new file mode 100644 index 0000000..ca8f001 --- /dev/null +++ b/Minmax-TOFU-2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f2c2b3c3b4cf0be1dd5f2b588ae893aad7554db9355c3492785868456bef603 +size 892563744 diff --git a/Minmax-TOFU-2.Q6_K.gguf b/Minmax-TOFU-2.Q6_K.gguf new file mode 100644 index 0000000..bf97de0 --- /dev/null +++ b/Minmax-TOFU-2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d177dd439abd97a21e90a977f28b22e3e475d01fd603f97fa23b1bb22c3dc6b6 +size 1021800736 diff --git a/Minmax-TOFU-2.Q8_0.gguf b/Minmax-TOFU-2.Q8_0.gguf new file mode 100644 index 0000000..0fcde3d --- /dev/null +++ b/Minmax-TOFU-2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:373d3452e6b0d1cec6a428c143cdf94cd57d4c0a028d1f2928ee24bc555f2dd5 +size 1321083168 diff --git a/Minmax-TOFU-2.f16.gguf b/Minmax-TOFU-2.f16.gguf new file mode 100644 index 0000000..30a4839 --- /dev/null +++ b/Minmax-TOFU-2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:044f0df74a6aa2875c39fc97b36ce2aee6e1779530acd86a2fe46a6305b9b71d +size 2479595808 diff --git a/README.md b/README.md new file mode 100644 index 0000000..62b4bd5 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Jiajunruan/Minmax-TOFU-2 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Jiajunruan/Minmax-TOFU-2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Minmax-TOFU-2-GGUF).*** + +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/Minmax-TOFU-2-GGUF/resolve/main/Minmax-TOFU-2.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Minmax-TOFU-2-GGUF/resolve/main/Minmax-TOFU-2.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Minmax-TOFU-2-GGUF/resolve/main/Minmax-TOFU-2.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Minmax-TOFU-2-GGUF/resolve/main/Minmax-TOFU-2.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Minmax-TOFU-2-GGUF/resolve/main/Minmax-TOFU-2.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Minmax-TOFU-2-GGUF/resolve/main/Minmax-TOFU-2.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Minmax-TOFU-2-GGUF/resolve/main/Minmax-TOFU-2.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Minmax-TOFU-2-GGUF/resolve/main/Minmax-TOFU-2.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Minmax-TOFU-2-GGUF/resolve/main/Minmax-TOFU-2.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Minmax-TOFU-2-GGUF/resolve/main/Minmax-TOFU-2.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Minmax-TOFU-2-GGUF/resolve/main/Minmax-TOFU-2.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Minmax-TOFU-2-GGUF/resolve/main/Minmax-TOFU-2.f16.gguf) | f16 | 2.6 | 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. + +