dipta007/GanitLLM-4B_SFT_CGRPO

Text Generation • 196k • Updated Jan 10 • 10

Note 4b final model with multi-stage training and curriculum GRPO

dipta007/GanitLLM-1.7B_SFT_CGRPO

Text Generation • 2B • Updated Jan 10 • 4

Note 1.7b final model with multi-stage training and curriculum GRPO

dipta007/GanitLLM-0.6B_SFT_CGRPO

Text Generation • 0.8B • Updated Jan 10 • 6

Note 0.6b final model with multi-stage training and curriculum GRPO