Unverified50% confidenceFactExact time
The author Nouamane previously also contributed to Ultra-Scale and Smol Training Playbooks.
1
Sources
50%
Confidence
Long-term
Relevance
11/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedTraining was done in a headless simulator the author wrote by hand in Rust, rather than running directly in the game itself.56% similarUnverifiedSmoLLM基础模型训练使用了来自FineWeb-Edu数据集的约25亿token54% similarUnverifiedThe author did not train from scratch, but continued training from a network built for an older version (warm start).52% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1140968API
curl https://kongchang.com/api/v1/knowledge/claims/1140968MCP
get_claim(id=1140968)