Chris Messina

Replit Code V1.5 3B - A new code generation language model

by
Top Hunter
β€’

Replit Code v1.5 is a 3.3B parameter Causal Language Model focused on Code Completion.

The model is trained in bfloat16 on 1T tokens of code (~200B tokens over 5 epochs, including linear cooldown) for 30 programming languages

Add a comment

Replies

Best
Chris Messina
Top Hunter
Hunter
πŸ“Œ
This is an impressive AI model that was released this past weekend at the AI Engineer Summit in San Francisco. The results are pretty solid β€” don't sleep on this.
Julien Ergan
Remarkable achievement, congratulations! Might be of interest: @naoto_shibata_morph, @oginokairan.
AndrΓ© J
How is this in comparison to GitHub copilots codex model?
Philipp Shay
Impressive launch! πŸš€ Good luck with your project! 🌟 How does your model handle complex code suggestions for multiple programming languages?
Yuki Ogino
Nice one! Congrats on the launch!
Ashish Kumar Gopalika
Looks interesting Excited to use it Congratulations πŸŽ‰
Esus πŸ›‘οΈ
Always love a Replit launch, Congrats @amasad and team! ⚑️
Narendra Solanki
Replit Code v1.5 is every coder's dream! Code completion to the next level. Bring it on!
Martin Baun
Replit's decision to make AI free for all users is commendable and reflects the growing importance of AI in software development. The new code generation language model, Replit Code V1.5 3B, looks promising, especially with its open-source approach. It's great to see AI becoming more accessible to the developer community. Thanks for sharing this update!
Ghost Kitty
Comment Deleted