HomeAI · summaries
Storia in 2 fonti
A $1,500 foundation model that rivals larger LLMs
Sapient researchers trained a 1B reasoning model on just 40B tokens — scoring competitively with 2B-7B models at a fraction of typical pretraining cost.
Confronto fonti
2 prospettive sulla stessa storiaTimeline cronologica
- ·
venturebeat.com
A $1,500 foundation model that rivals larger LLMs
Sapient researchers trained a 1B reasoning model on just 40B tokens — scoring competitively with 2B-7B models at a fraction of typical pretraining cost.
- ·
cryptobriefing.com
Sapient trains 1B-parameter HRM-Text model for $1,500 in 1.9 days
Sapient Intelligence trained HRM-Text, a 1.15B-parameter open-source language model, for just $1,500 in 1.9 days using 16 GPUs and 40 billion tokens.