---
datasets:
- bigcode/the-stack
---
# hexcoder 3b (replit)

![hex_stickers](https://www.mitchelloharawild.com/blog/2018-07-10-hexwall_files/figure-html/final-1.png)

This is a model that trains the base [replit code model](https://huggingface.co/replit/replit-code-v1-3b) 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.