VeriPrefer
Collection
Models and data for the paper "Insights from Verification: Training a Verilog Generation LLM with Reinforcement Learning from Testbench Feedback"
•
10 items
•
Updated
•
2
Check https://github.com/CatIIIIIIII/VeriPrefer for usage.
Base model
deepseek-ai/deepseek-coder-7b-instruct-v1.5