commit e81f6298813ff7ab9abc110cecac8e799fe941f7 Author: ModelHub XC Date: Tue Sep 8 09:30:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MiniLLM-0.2B-WithWudao-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..54cde82 --- /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 +MiniLLM-0.2B-WithWudao.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MiniLLM-0.2B-WithWudao.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MiniLLM-0.2B-WithWudao.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MiniLLM-0.2B-WithWudao.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MiniLLM-0.2B-WithWudao.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MiniLLM-0.2B-WithWudao.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MiniLLM-0.2B-WithWudao.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MiniLLM-0.2B-WithWudao.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MiniLLM-0.2B-WithWudao.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MiniLLM-0.2B-WithWudao.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MiniLLM-0.2B-WithWudao.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MiniLLM-0.2B-WithWudao.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MiniLLM-0.2B-WithWudao.IQ4_XS.gguf b/MiniLLM-0.2B-WithWudao.IQ4_XS.gguf new file mode 100644 index 0000000..6dbe005 --- /dev/null +++ b/MiniLLM-0.2B-WithWudao.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:567c6ac4cb1a87e7e033bab878c32dc79a1e79385923d7c5236f61ed0090ed00 +size 173474240 diff --git a/MiniLLM-0.2B-WithWudao.Q2_K.gguf b/MiniLLM-0.2B-WithWudao.Q2_K.gguf new file mode 100644 index 0000000..18906c4 --- /dev/null +++ b/MiniLLM-0.2B-WithWudao.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a005a7a805d8b978b2e85ec7700ab67431f263b347b9843db37a88741ad2730b +size 138063232 diff --git a/MiniLLM-0.2B-WithWudao.Q3_K_L.gguf b/MiniLLM-0.2B-WithWudao.Q3_K_L.gguf new file mode 100644 index 0000000..25a1bf9 --- /dev/null +++ b/MiniLLM-0.2B-WithWudao.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:148a5a3a4c48f9ced0daf2f0d47199dac5acf51098ce56182afd85b3b1394ac0 +size 167055264 diff --git a/MiniLLM-0.2B-WithWudao.Q3_K_M.gguf b/MiniLLM-0.2B-WithWudao.Q3_K_M.gguf new file mode 100644 index 0000000..a620af1 --- /dev/null +++ b/MiniLLM-0.2B-WithWudao.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96812e225992377c3d274d906f68b79f709aa927ceb7b5bd8b35d5708d78f6e7 +size 162058144 diff --git a/MiniLLM-0.2B-WithWudao.Q3_K_S.gguf b/MiniLLM-0.2B-WithWudao.Q3_K_S.gguf new file mode 100644 index 0000000..81c4ccc --- /dev/null +++ b/MiniLLM-0.2B-WithWudao.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cf5c121d0f266160c0999a66fb583ba26a90a8dcd83daa622927b095c6b87a6 +size 154226592 diff --git a/MiniLLM-0.2B-WithWudao.Q4_K_M.gguf b/MiniLLM-0.2B-WithWudao.Q4_K_M.gguf new file mode 100644 index 0000000..13fc8f8 --- /dev/null +++ b/MiniLLM-0.2B-WithWudao.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d2b4989e406ce3823c6c9870c5ef66e6edf83044f0950f305dfee0dbd15f30e +size 190895328 diff --git a/MiniLLM-0.2B-WithWudao.Q4_K_S.gguf b/MiniLLM-0.2B-WithWudao.Q4_K_S.gguf new file mode 100644 index 0000000..e0872ba --- /dev/null +++ b/MiniLLM-0.2B-WithWudao.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf0d228ab68672bf7e4c918ab73e1c61c04727630dd07dd18a2e73f9833c83d0 +size 183633120 diff --git a/MiniLLM-0.2B-WithWudao.Q5_K_M.gguf b/MiniLLM-0.2B-WithWudao.Q5_K_M.gguf new file mode 100644 index 0000000..542c847 --- /dev/null +++ b/MiniLLM-0.2B-WithWudao.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b0738a1c601377f2fea1788e773b3d9e743564de28757cc7dc9745d4c638249 +size 214204768 diff --git a/MiniLLM-0.2B-WithWudao.Q5_K_S.gguf b/MiniLLM-0.2B-WithWudao.Q5_K_S.gguf new file mode 100644 index 0000000..dbd3cf7 --- /dev/null +++ b/MiniLLM-0.2B-WithWudao.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88f1af678aa5656ba76403176b1f5edca92f0cf8780d4cf8d36f6909cbff201c +size 208085344 diff --git a/MiniLLM-0.2B-WithWudao.Q6_K.gguf b/MiniLLM-0.2B-WithWudao.Q6_K.gguf new file mode 100644 index 0000000..434881a --- /dev/null +++ b/MiniLLM-0.2B-WithWudao.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03db79111bc32116fcd111ee6d00901493f6bab5a29a991bc9ae6e944a85e84c +size 243132096 diff --git a/MiniLLM-0.2B-WithWudao.Q8_0.gguf b/MiniLLM-0.2B-WithWudao.Q8_0.gguf new file mode 100644 index 0000000..a6367a5 --- /dev/null +++ b/MiniLLM-0.2B-WithWudao.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72b450121d4484ceb4cbb6960005e5c281122b227e722038007030b12799ca38 +size 303838976 diff --git a/MiniLLM-0.2B-WithWudao.f16.gguf b/MiniLLM-0.2B-WithWudao.f16.gguf new file mode 100644 index 0000000..71c54fc --- /dev/null +++ b/MiniLLM-0.2B-WithWudao.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52c70665ff928fe5eb016cb53c152c28ab7293c43e7d0041b5f054302b7eef82 +size 570536576 diff --git a/README.md b/README.md new file mode 100644 index 0000000..65a979e --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: Tongjilibo/MiniLLM-0.2B-Base +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Tongjilibo/MiniLLM-0.2B-Base + + +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/MiniLLM-0.2B-WithWudao-GGUF/resolve/main/MiniLLM-0.2B-WithWudao.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/MiniLLM-0.2B-WithWudao-GGUF/resolve/main/MiniLLM-0.2B-WithWudao.Q3_K_S.gguf) | Q3_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/MiniLLM-0.2B-WithWudao-GGUF/resolve/main/MiniLLM-0.2B-WithWudao.Q3_K_M.gguf) | Q3_K_M | 0.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MiniLLM-0.2B-WithWudao-GGUF/resolve/main/MiniLLM-0.2B-WithWudao.Q3_K_L.gguf) | Q3_K_L | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/MiniLLM-0.2B-WithWudao-GGUF/resolve/main/MiniLLM-0.2B-WithWudao.IQ4_XS.gguf) | IQ4_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/MiniLLM-0.2B-WithWudao-GGUF/resolve/main/MiniLLM-0.2B-WithWudao.Q4_K_S.gguf) | Q4_K_S | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MiniLLM-0.2B-WithWudao-GGUF/resolve/main/MiniLLM-0.2B-WithWudao.Q4_K_M.gguf) | Q4_K_M | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MiniLLM-0.2B-WithWudao-GGUF/resolve/main/MiniLLM-0.2B-WithWudao.Q5_K_S.gguf) | Q5_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/MiniLLM-0.2B-WithWudao-GGUF/resolve/main/MiniLLM-0.2B-WithWudao.Q5_K_M.gguf) | Q5_K_M | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/MiniLLM-0.2B-WithWudao-GGUF/resolve/main/MiniLLM-0.2B-WithWudao.Q6_K.gguf) | Q6_K | 0.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MiniLLM-0.2B-WithWudao-GGUF/resolve/main/MiniLLM-0.2B-WithWudao.Q8_0.gguf) | Q8_0 | 0.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MiniLLM-0.2B-WithWudao-GGUF/resolve/main/MiniLLM-0.2B-WithWudao.f16.gguf) | f16 | 0.7 | 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. + +