Readme
CodeLlama is a family of fine-tuned Llama 2 models for coding. This is CodeLlama-70b-Instruct, a 70 billion parameter Llama model tuned for chatting about code.
meta
/
codellama-70b-instruct
A 70 billion parameter Llama tuned for coding and conversation
Input
Output
Run time and cost
This model runs on Nvidia A100 (80GB) GPU hardware. Predictions typically complete within 70 seconds. The predict time for this model varies significantly based on the inputs.