meta / codellama-7b

A 7 billion parameter Llama tuned for coding and conversation

  • Public
  • 15K runs
  • GitHub
  • Paper
  • License



Run time and cost

This model runs on Nvidia A40 (Large) GPU hardware. Predictions typically complete within 1 seconds.


CodeLlama is a family of fine-tuned Llama 2 models for coding. This is CodeLlama-7b, a 7 billion parameter Llama model tuned for completing code.