Code LLaMA
An open-source large language model used in an experiment where students using ChatGPT and Code LLaMA performed worse on a test without tools compared to those using only Google.
Common Themes
Videos Mentioning Code LLaMA
Making Transformers Sing - with Mikey Shulman of Suno
Latent Space
A code generation model trained on both code and English, used as an analogy for why Suno trains its music models on data beyond just music.
The Four Wars of the AI Stack - Dec 2023 Recap
Latent Space
A code model mentioned in the discussion about code models.
The "Normsky" architecture for AI coding agents — with Beyang Liu + Steve Yegge of SourceGraph
Latent Space
An open-source model that Sourcegraph is not currently using but continuously evaluates against other available models.
Beating GPT-4 with Open Source Models - with Michael Royzen of Phind
Latent Space
A large language model from Meta AI specifically trained for coding tasks, mentioned as the base model for Phind's fine-tuned models.
The End of Finetuning — with Jeremy Howard of Fast.ai
Latent Space
A fine-tuned version of Llama 2 by Meta, which became good at coding but at the cost of forgetting other capabilities (catastrophic forgetting).
Applying AI to Education
MIT Open Learning
An open-source large language model used in an experiment where students using ChatGPT and Code LLaMA performed worse on a test without tools compared to those using only Google.