SkyworkAI/Skywork
A series of 13B-parameter LLMs developed by Kunlun Group's Skywork team, trained on 3.2 trillion tokens of multilingual and code data.
Not currently ranked — collecting fresh signals.
star history
Skywork is a family of open-source large language models ranging from base to specialized variants including chat, math, and multimodal versions. The models were pre-trained on 3.2TB of high-quality multilingual data (primarily Chinese and English) and code. The project releases not only the model weights but also the training data, evaluation data, and evaluation methods for reproducibility. Quantized versions are provided to enable deployment on consumer-grade GPUs.
Frequently asked
- What is SkyworkAI/Skywork?
- A series of 13B-parameter LLMs developed by Kunlun Group's Skywork team, trained on 3.2 trillion tokens of multilingual and code data.
- Is Skywork open source?
- Yes — SkyworkAI/Skywork is an open-source project tracked on heatdrop.
- What language is Skywork written in?
- SkyworkAI/Skywork is primarily written in Python.
- How popular is Skywork?
- SkyworkAI/Skywork has 1.5k stars on GitHub.
- Where can I find Skywork?
- SkyworkAI/Skywork is on GitHub at https://github.com/SkyworkAI/Skywork.