dipta007/dagger-4B_GRPO
Text Generation • 4B • Updated • 663
Shubhashis Roy Dipta PRO
dipta007
AI & ML interests
Multimodal Understanding, Reasoning, Generation
Recent Activity
upvoted a paper 6 days ago
PA3: Policy-Aware Agent Alignment through Chain-of-Thought upvoted a paper 11 days ago
†DAGGER: Distractor-Aware Graph Generation for Executable Reasoning in Math ProblemsOrganizations
dipta007/dagger-4B_SFT
Text Generation • 4B • Updated • 666 • 1
dipta007/dagger-4B_SFT_GRPO
Text Generation • 4B • Updated • 656
dipta007/dagger-12B_GRPO
Text Generation • 12B • Updated • 647
dipta007/dagger-12B_SFT
Text Generation • 12B • Updated • 656 • 1
dipta007/dagger-12B_SFT_GRPO
Text Generation • 12B • Updated • 648 • 1
dipta007/decomposeRL-7b
Text Generation • 8B • Updated • 11
dipta007/atomicity-is-question-judge-balanced
Text Classification • 0.4B • Updated • 11
dipta007/atomicity-single-focus-judge-balanced
Text Classification • 0.4B • Updated • 6
dipta007/atomicity-no-conjunctions-judge-balanced
Text Classification • 0.4B • Updated • 6
dipta007/atomicity-verifiable-judge-balanced
Text Classification • 0.4B • Updated • 14
dipta007/atomicity-grounded-judge-balanced
Text Classification • 0.4B • Updated • 9
dipta007/question-judge-balanced
Text Classification • 0.4B • Updated • 7
dipta007/coverage-judge-balanced
Text Classification • 0.4B • Updated • 6
dipta007/answer-judge-balanced
Text Classification • 0.4B • Updated • 14
dipta007/VCInspector-7B
Image-Text-to-Text • 8B • Updated • 44 • 1
dipta007/VCInspector-3B
Image-Text-to-Text • 4B • Updated • 14 • 1
dipta007/GanitLLM-0.6B_CGRPO
Text Generation • 0.6B • Updated • 13
dipta007/GanitLLM-0.6B-SFT
Text Generation • 0.8B • Updated • 17
dipta007/GanitLLM-0.6B_SFT_GRPO
Text Generation • 0.8B • Updated • 13
dipta007/GanitLLM-0.6B_SFT_CGRPO
Text Generation • 0.8B • Updated • 15
dipta007/GanitLLM-1.7B_CGRPO
Text Generation • 2B • Updated • 11
dipta007/GanitLLM-1.7B-SFT
Text Generation • 2B • Updated • 7
dipta007/GanitLLM-1.7B_SFT_GRPO
Text Generation • 2B • Updated • 7
dipta007/GanitLLM-1.7B_SFT_CGRPO
Text Generation • 2B • Updated • 12
dipta007/GanitLLM-4B_CGRPO
Text Generation • 4B • Updated • 26
dipta007/GanitLLM-4B-SFT
Text Generation • 196k • Updated • 153 •
dipta007/GanitLLM-4B_SFT_GRPO
Text Generation • 196k • Updated • 10 • 1
dipta007/GanitLLM-4B_SFT_CGRPO
Text Generation • 196k • Updated • 126
dipta007/TigerLLM-9B-it
12B • Updated • 11