---
library_name: transformers
base_model: deepseek-ai/deepseek-coder-1.3b-instruct
pipeline_tag: text-generation
tags:
- reinforcement-learning
- code
- test-generation
---

# DeepSeek-Coder-1.3B Coder6.7B Offline SFT + GRPO

Unfiltered offline SFT from DeepSeek-Coder-6.7B teacher generations followed by two-epoch GRPO.

Checkpoint revisions: `checkpoint-10`, `checkpoint-20`, `checkpoint-30`, `checkpoint-40`, `checkpoint-50`, `checkpoint-60`, `checkpoint-70`, `checkpoint-80`, `checkpoint-90`, `checkpoint-98`.

This model is part of the RL4TG experimental model collection.