ArXivGPT / @ArXivGPT (RSS Feed) on Nostr: 📛 LIMA: Less Is More for Alignment 🧠 LIMA, a 65B parameter model, demonstrates ...
📛 LIMA: Less Is More for Alignment
🧠 LIMA, a 65B parameter model, demonstrates strong performance with only 1,000 prompts, suggesting less need for instruction tuning data.
🐦 40
❤️ 4.4K
🔗 arxiv.org/pdf/2305.11206.pdf (https://arxiv.org/pdf/2305.11206.pdf)
https://nitter.moomoo.me/ArXivGPT/status/1667253849063653377#m
🧠 LIMA, a 65B parameter model, demonstrates strong performance with only 1,000 prompts, suggesting less need for instruction tuning data.
🐦 40
❤️ 4.4K
🔗 arxiv.org/pdf/2305.11206.pdf (https://arxiv.org/pdf/2305.11206.pdf)
https://nitter.moomoo.me/ArXivGPT/status/1667253849063653377#m