-
tensorfiend/gemma4-4b-sft-20260920-564-best
Text Generation • 8B • Updated • 20 -
tensorfiend/tunelm-gemma4-4b-sft-20260921-1692-final
Text Generation • 8B • Updated • 24 -
tensorfiend/tunelm-gemma4-4b-sft-20260921-1680-best
Text Generation • 8B • Updated • 6 -
tensorfiend/tunelm-gemma4-4b-sft-quality-20260927-86-best
Text Generation • 8B • Updated • 32
🤝 Open to Collab
Shanmukha Sainath
tensorfiend
AI & ML interests
NLP, RL
Recent Activity
upvoted a collection 4 days ago
Sand3D upvoted a collection 12 days ago
💧 LFM3 liked a model about 1 month ago
google/embeddinggemma-2Organizations
None yet
SimpleThoughts data spans four stages—pretraining, SFT, alignment, and reasoning - training DotLM-165M to prioritize reasoning over memorization.
-
tensorfiend/gemma4-4b-sft-20260920-564-best
Text Generation • 8B • Updated • 20 -
tensorfiend/tunelm-gemma4-4b-sft-20260921-1692-final
Text Generation • 8B • Updated • 24 -
tensorfiend/tunelm-gemma4-4b-sft-20260921-1680-best
Text Generation • 8B • Updated • 6 -
tensorfiend/tunelm-gemma4-4b-sft-quality-20260927-86-best
Text Generation • 8B • Updated • 32
SimpleThoughts data spans four stages—pretraining, SFT, alignment, and reasoning - training DotLM-165M to prioritize reasoning over memorization.