Edge 324: A Deep Dive Into Code Llama: Meta AI’s Open Source Entrance in the Code LLM Space
The new model builds on Llama2 and includes Python and Instruction following specialized versions.
Coding has rapidly become one of the most active theaters of action for the large language models(LLMs). Since OpenAI unveiled Codex( now part of GPT-4) last year, the level of innovation in coding language models has been breathtaking. In the last few months, we have seen code LLMs released by companies like Salesforce, Hugging Face, DeepMind, Amazon and many others. A few days ago, Meta AI jumped the code LLM frenzy with the release of Code Llama, an open-source code LLM based on the recently released Llama 2. The release of Code Llama is significant given the impact that Meta is having in the open-source foundation model movement
Meta AI has developed Code Llama, a specialized iteration of Llama 2 that emerged through extended training on datasets specific to coding. By intensively extracting data from the code-centric dataset, Code Llama evolved to bolster its coding proficiency, effectively enhancing the capabilities inherited from Llama 2. This advanced version demonstrates prowess in code generation and articulating natural language about code.