SimpleThoughts data spans four stages—pretraining, SFT, alignment, and reasoning - training DotLM-165M to prioritize reasoning over memorization.
Open to Collab
Shanmukha Sainath
tensorfiend
AI & ML interests
NLP, RL
Recent Activity
updated a dataset about 2 months ago
tensorfiend/SimpleThoughts updated a collection about 2 months ago
Feedback Prize kaggle updated a collection about 2 months ago
DotLMOrganizations
None yet