https://huggingface.co/CNWPlayer/VegaLM1-42M-Base further trained on another roughly 2.8B tokens of stack-v3-train. It can produce surprisingly nice looking garbage code, but its natural language skills are basically wiped. Dare I say, it's SOTA for <90M coding models?
- Downloads last month
- 7
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for CNWPlayer/VegaLM1-42M-CodeCompletion
Base model
CNWPlayer/VegaLM1-42M-Base