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

Dirhousssi Amine
@DirhousssiAmine
๐Ÿ‡ฒ๐Ÿ‡ฆ ML engineer - post training team @huggingface ๐Ÿค— Rustacean ๐Ÿฆ€ โ— BJJ competitor โ— Lifelong Martial Artist
๊ฐ€์ž… March 2013
444 ํŒ”๋กœ์ž‰ ์ค‘    643 ํŒฌ
First multi-turn agent harness RL training with sandboxing running at scale on the Hub ๐ŸŽ‰ ๐Ÿค— Spawned 9,523 sandboxes in 14h. Qwen3-Coder-30B-A3B (30B MoE) trained in full, FSDP2 + expert parallel. All on HF Jobs. No Slurm anywhere. 0 crashes ๐Ÿค—
๋” ๋ณด๊ธฐ