metadata
datasets:
- bigcode/the-stack
hexcoder 3b (replit)
This is a model that trains the base replit code model on R coding instructions, which are brief questions to which I have formulated a brief anwser.
Then I intend to instruction tune the model on all stackoverflow questions and anwsers with the tag 'r' in the 2011 to 2016 timeframe, presenting stackoverflow questions as <|user|> and the best answer as <|assistant|>. This will teach the model that it is expected to produce an answer to a user's question about 'r'.
The intended outcome is a reasonably adequate model which can answer basic r user questions, but more broadly an evaluaion of the data/sources and training needed to produce great open source code generating models for r.