FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language Paper • 2506.20920 • Published 4 days ago • 37
math-extraction-comp/HuggingFaceH4__R2-Q7B-GR1-ALL-s1k-5e-5-weight-decay-1e-4_private Viewer • Updated Feb 10 • 30 • 32
math-extraction-comp/HuggingFaceH4__R2-Q7B-GR1-ALL-s1k-5e-5-weight-decay-1e-4_private Viewer • Updated Feb 10 • 30 • 32
SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model Paper • 2502.02737 • Published Feb 4 • 235
math-extraction-comp/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B_private Viewer • Updated Feb 6 • 500 • 30