๊ฐ€์ž… ํ›„ ์ดˆ๋Œ€ ๋งํฌ๋ฅผ ๊ณต์œ ํ•˜๋ฉด ๋™์˜์ƒ ์žฌ์ƒ ๋ฐ ์ดˆ๋Œ€ ๋ณด์ƒ์„ ๋ฐ›์„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

Lewis Tunstall
@_lewtun
๐Ÿค  post-training @huggingface
๊ฐ€์ž… August 2018
549 ํŒ”๋กœ์ž‰ ์ค‘    20.4K ํŒฌ
Good timing by DeepSeek to release just after we removed support for seq2seq models in TRL ๐Ÿ˜