Unbounded Labs releases Bart, a 2.82B vintage LLM
Bart is a 2.82B-parameter LLM trained from scratch on 20.1B tokens of English written before 1931, after 3 months and $800 in compute. A live demo is available.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Apple cuts jobs across Vision Pro, Siri teams to refocus on AI
- Tibo discusses Codex, ultrafast AI, and OpenAI vs Anthropic
- Instinct AI assistant raises privacy and security concerns
- MiniMax M3 and M2.7 models offer unlimited access on GMI Cloud
- Ethan Mollick: AI-written submissions are obvious to readers