LLaMA-13B beat GPT-3 on most benchmarks; leaked weights broke the monopoly
alex_verem · x · 2026-10-13
Thread entry #3: Meta's LLaMA (arXiv 2302.13971), a 7B–65B family trained on trillions of tokens from public datasets only. LLaMA-13B beats GPT-3 (175B) on most benchmarks; LLaMA-65B matches Chinchilla-70B and PaLM-540B. The tweet notes weights leaked within a week, ending big labs' monopoly on frontier-capable models.
More from Research
- Graph theorist spends 20 hours on OpenAI Math Dump, finds solutions to his decade-old conjectures — burny_tech · 2026-10-13
- tszzl predicts mechinterp progress in coming months unlike anything in years — tszzl · 2026-10-13
- Free ML Workshop on the Math Discord Server Covers ML, Deep Learning and Graphs — zeroalephzeta · 2026-10-13
- sansreplace: a novel O(k log k) sampling-without-replacement algorithm with zero extra memory — burny_tech · 2026-10-13
- New Paper Explains Mamba-3's State Rotations as Underdamped Second-Order Dynamics — tri_dao · 2026-10-13
- New Paper Gives Exact Pricing and Analytic Risk Attribution for First-to-Default Basket Swaps — DrCirillo · 2026-10-13