#79 · Primary category: Foundation Models

Skywork

llm

Skywork series models are pre-trained on 3.2TB of high-quality multilingual (mainly Chinese and English) and code data. We have open-sourced the model, training data, evaluation data, evaluation methods, etc.

Project last updated:03/07/25

GitHub Stars

1.5K

Forks

148

Contributors

7

License

Other

Why we included this project

Skywork is a bilingual Chinese-English model family that open-sources not just the weights but the training data, evaluation data, and evaluation methods, so a small team can study how a 13B-scale model is actually built rather than treat it as a black box. The repo includes a base, chat, math, and multimodal variant, plus quantized checkpoints sized for consumer GPUs. The documentation covers a 3.2-trillion-token pretraining recipe and the benchmarks used, which makes it feasible to reproduce comparisons against other 13B models. Teams working primarily in Chinese or wanting a lightweight local deployment are the most obvious audience. One thing to check first: the project uses a custom community license, not a standard open-source one, so read the terms before commercial use.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category