All activity
VerifAI Incleft a comment
With a new Large Language Model (LLM) every week, it is becoming impossible to choose the best LLM for coding. VerifAI's MultiLLM generates code from multiple LLMs and picks the best result. VerifAI's MultiLLM reduces LLM hallucinations and gets us closer to the ground truth!
MultiLLMGenerate Code from Multiple LLMs and pick the Best Result
VerifAI's open-source MultiLLM framework generates Code by calling LLMs in parallel and ranks their outputs to find the best results. MultiLLM can be extended to support new LLMs and custom ranking function to evaluate a variety of outputs from LLMs.
MultiLLMGenerate Code from Multiple LLMs and pick the Best Result