SimpleThoughts data spans four stages—pretraining, SFT, alignment, and reasoning - training DotLM-165M to prioritize reasoning over memorization.
Shanmukha Sainath
tensorfiend
AI & ML interests
NLP, RL
Recent Activity
updated a dataset about 12 hours ago
tensorfiend/SimpleThoughts updated a collection 1 day ago
Feedback Prize kaggle updated a collection 1 day ago
DotLMOrganizations
None yet