CodeLlama 70B Instruct

CodeLlama 70B Instruct is a large-scale generative text model with 70 billion parameters, specifically designed for code synthesis and understanding tasks. Fine-tuned to follow user instructions effectively, it excels in interactive coding environments, supporting tasks such as code completion, infilling, and explanation. The model is optimized for efficient processing and is suitable for both commercial and research applications in English and various programming languages. While it offers advanced capabilities for AI-assisted coding, it's important to note that it doesn't support long contexts of up to 100k tokens, which may limit its use with extensive codebases. For more details, refer to the model's Hugging Face page .

Information

Family:
Code Llama
Released:
January 29, 2024
Parameters:
70B
Context:
16K
Variant:
code
Expert:
None
Repository:
HuggingFace
Knowledge Cutoff: