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

MiniMax (official)
@MiniMax_AI
Code: @MiniMax_Code MiniMax Design: @Hailuo_AI API: M Plan:
๊ฐ€์ž… January 2025
1K ํŒ”๋กœ์ž‰ ์ค‘    130K ํŒฌ
Thanks to the NVIDIA NeMo team for day-0 fine-tuning support for MiniMax-M3.1-Flash! ๐Ÿฐ What magic will this ๐Ÿฐ bring in the post train scenario?
Youโ€™ve probably already used it: Space Bunny pushed 200T+ tokens before anyone knew it was MiniMax-M3.1-Flash. Now itโ€™s open weights ๐Ÿ”ฅ Thank you @MiniMax_AI for open sourcing it! Day-0 fine-tuning in NVIDIA NeMo-AutoModel โœ… FSDP2, expert, pipeline, and context parallelism, โœ…scaling up to 128 GPUs, and the NVFP4 checkpoint loads directly.
๋” ๋ณด๊ธฐ