commit a456dddd3f9e31bff4bbfaa29ece429a1cfec7c1 Author: ModelHub XC Date: Thu Jun 11 16:46:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/YuLan-Mini-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5d73c90 --- /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 +YuLan-Mini.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +YuLan-Mini.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +YuLan-Mini.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +YuLan-Mini.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +YuLan-Mini.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +YuLan-Mini.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +YuLan-Mini.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +YuLan-Mini.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +YuLan-Mini.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +YuLan-Mini.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +YuLan-Mini.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +YuLan-Mini.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..334e232 --- /dev/null +++ b/README.md @@ -0,0 +1,101 @@ +--- +arxiv: 2412.17743 +base_model: yulan-team/YuLan-Mini +datasets: +- yulan-team/YuLan-Mini-Datasets +- HuggingFaceFW/fineweb-edu +- bigcode/the-stack-v2 +- mlfoundations/dclm-baseline-1.0 +- math-ai/AutoMathText +- gair-prox/open-web-math-pro +- RUC-AIBOX/long_form_thought_data_5k +- internlm/Lean-Workbook +- internlm/Lean-Github +- deepseek-ai/DeepSeek-Prover-V1 +- ScalableMath/Lean-STaR-base +- ScalableMath/Lean-STaR-plus +- ScalableMath/Lean-CoT-base +- ScalableMath/Lean-CoT-plus +- opencsg/chinese-fineweb-edu +- liwu/MNBVC +- vikp/textbook_quality_programming +- HuggingFaceTB/smollm-corpus +- OpenCoder-LLM/opc-annealing-corpus +- OpenCoder-LLM/opc-sft-stage1 +- OpenCoder-LLM/opc-sft-stage2 +- XinyaoHu/AMPS_mathematica +- deepmind/math_dataset +- mrfakename/basic-math-10m +- microsoft/orca-math-word-problems-200k +- AI-MO/NuminaMath-CoT +- HuggingFaceTB/cosmopedia +- MU-NLPC/Calc-ape210k +- manu/project_gutenberg +- storytracer/LoC-PD-Books +- allenai/dolma +language: +- en +- zh +library_name: transformers +license: mit +quantized_by: mradermacher +tags: +- code +- math +--- +## About + + + + + + +static quants of https://huggingface.co/yulan-team/YuLan-Mini + + +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/YuLan-Mini-GGUF/resolve/main/YuLan-Mini.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/YuLan-Mini-GGUF/resolve/main/YuLan-Mini.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/YuLan-Mini-GGUF/resolve/main/YuLan-Mini.IQ4_XS.gguf) | IQ4_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/YuLan-Mini-GGUF/resolve/main/YuLan-Mini.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/YuLan-Mini-GGUF/resolve/main/YuLan-Mini.Q3_K_L.gguf) | Q3_K_L | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/YuLan-Mini-GGUF/resolve/main/YuLan-Mini.Q4_K_S.gguf) | Q4_K_S | 1.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/YuLan-Mini-GGUF/resolve/main/YuLan-Mini.Q4_K_M.gguf) | Q4_K_M | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/YuLan-Mini-GGUF/resolve/main/YuLan-Mini.Q5_K_S.gguf) | Q5_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/YuLan-Mini-GGUF/resolve/main/YuLan-Mini.Q5_K_M.gguf) | Q5_K_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/YuLan-Mini-GGUF/resolve/main/YuLan-Mini.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/YuLan-Mini-GGUF/resolve/main/YuLan-Mini.Q8_0.gguf) | Q8_0 | 2.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/YuLan-Mini-GGUF/resolve/main/YuLan-Mini.f16.gguf) | f16 | 5.0 | 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/YuLan-Mini.IQ4_XS.gguf b/YuLan-Mini.IQ4_XS.gguf new file mode 100644 index 0000000..9682b12 --- /dev/null +++ b/YuLan-Mini.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f25ed9a53e308eb98d6c670851a4e51c2c86aedd964857a8be8554f60d1e9619 +size 1482524416 diff --git a/YuLan-Mini.Q2_K.gguf b/YuLan-Mini.Q2_K.gguf new file mode 100644 index 0000000..fdca10b --- /dev/null +++ b/YuLan-Mini.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d85989a79ed337a32272417e1045ad62739ed7362d573f8928fec49067b1e2ea +size 1467847936 diff --git a/YuLan-Mini.Q3_K_L.gguf b/YuLan-Mini.Q3_K_L.gguf new file mode 100644 index 0000000..5a5eef1 --- /dev/null +++ b/YuLan-Mini.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:074f130c0cbb29714f95b2f6dd9ae68acd1ae6186668aa77373d13a3375e9c76 +size 1605903616 diff --git a/YuLan-Mini.Q3_K_M.gguf b/YuLan-Mini.Q3_K_M.gguf new file mode 100644 index 0000000..8953ba6 --- /dev/null +++ b/YuLan-Mini.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0574cb5a45171df677da222967fe44e61d0e9cf74da6453ac16039f034b93cd +size 1559984896 diff --git a/YuLan-Mini.Q3_K_S.gguf b/YuLan-Mini.Q3_K_S.gguf new file mode 100644 index 0000000..0aa4091 --- /dev/null +++ b/YuLan-Mini.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62e2d5b50038588a2d9ef4c1c15a8bdae08fb4aadf89661e374deb1c4a915e58 +size 1462686976 diff --git a/YuLan-Mini.Q4_K_M.gguf b/YuLan-Mini.Q4_K_M.gguf new file mode 100644 index 0000000..85716cf --- /dev/null +++ b/YuLan-Mini.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af59ec8114c1ae4684c49cd964dacd16c80df178d3f601cf379a1db05fda37a7 +size 1846423936 diff --git a/YuLan-Mini.Q4_K_S.gguf b/YuLan-Mini.Q4_K_S.gguf new file mode 100644 index 0000000..3937b00 --- /dev/null +++ b/YuLan-Mini.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee9c278355778ec7e6cd81aa3aa5dfe73b0fc16c898ab4601ce995854a469cd9 +size 1746130816 diff --git a/YuLan-Mini.Q5_K_M.gguf b/YuLan-Mini.Q5_K_M.gguf new file mode 100644 index 0000000..84b5d89 --- /dev/null +++ b/YuLan-Mini.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:757214bd52db32a5a54f7afff98fc5c8c2ab73dba4a9597c9a04f8f56a416055 +size 1968619456 diff --git a/YuLan-Mini.Q5_K_S.gguf b/YuLan-Mini.Q5_K_S.gguf new file mode 100644 index 0000000..db68c4e --- /dev/null +++ b/YuLan-Mini.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ddb7a3df1069bb41ed660875ae68f198dd9d7b6fc130a0a834da9e907cecb66 +size 1881528256 diff --git a/YuLan-Mini.Q6_K.gguf b/YuLan-Mini.Q6_K.gguf new file mode 100644 index 0000000..11314b8 --- /dev/null +++ b/YuLan-Mini.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e28748b1bda8b90f54faaf20cd626fed84f5756f6774ec86fa75d3f923177510 +size 2579597056 diff --git a/YuLan-Mini.Q8_0.gguf b/YuLan-Mini.Q8_0.gguf new file mode 100644 index 0000000..54e9e0f --- /dev/null +++ b/YuLan-Mini.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ce7b6eacea95941d57a2ed3935b94b95d704e4d38f5354238cef986bf80d391 +size 2579597056 diff --git a/YuLan-Mini.f16.gguf b/YuLan-Mini.f16.gguf new file mode 100644 index 0000000..10413d7 --- /dev/null +++ b/YuLan-Mini.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d42596afa454acc91dec87f9ed740dc6753fb509054dff319aa7eb096a61c79 +size 4852003456