mehuldamani/RLCR-hotpot-octo
Text Generation • 8B • Updated
• 3 • 1
Mehul Damani PRO
mehuldamani
AI & ML interests
Reinforcement Learning, Large Language Models
Recent Activity
published
a dataset about 20 hours ago
mehuldamani/multi-answer-sft-target-dataset published
a model 2 days ago
mehuldamani/sfted_rlvr_multi__veryHardDataset_moreThinking updated
a dataset 2 days ago
mehuldamani/multi-answer-sft-target-dataset Organizations
None yet
mehuldamani/RLVR-hotpot-octo
Text Generation • 8B • Updated
• 2
mehuldamani/RLCR-hotpot-olmo-v2
Text Generation • 7B • Updated
• 1
mehuldamani/RLCR-hotpot-olmo
Text Generation • 7B • Updated
• 2
mehuldamani/RLVR-hotpot-olmo
Text Generation • 7B • Updated
• 1
mehuldamani/RLVR-hotpot-mistral
Text Generation • 7B • Updated
• 2
mehuldamani/calibration-only-v4
Text Generation • 8B • Updated
• 2
mehuldamani/bandit-log-RLCR-v2
Text Generation • 8B • Updated
• 2
mehuldamani/bandit-brier-RLCR-v1
Text Generation • 8B • Updated
• 2
mehuldamani/bandit-log-RLCR-v1
Text Generation • 8B • Updated
• 1
mehuldamani/toy-log-RLCR-v3
Text Generation • 8B • Updated
• 3 • 1
mehuldamani/toy-log-RLCR-v1
Text Generation • 8B • Updated
• 2
mehuldamani/RLVR-hotpot-gemma
Updated
mehuldamani/RLCR-hotpot-llama-base
Updated
mehuldamani/RLCR-hotpot-mistral
Updated
mehuldamani/nov15_qwen3_8b_math_rlVr_single
Updated
mehuldamani/calibration-only-v3
Updated
mehuldamani/nov15_qwen3_8b_math_rlcr_single
Updated
mehuldamani/nov15_qwen3_8b_math_rlcr_multiple
Updated
mehuldamani/RLCR-math-tac-v2
Updated
mehuldamani/RLVR-hotpot-llama
Updated
mehuldamani/RLCR-hotpot-llama
Updated
mehuldamani/RLCR-hotpot-log-loss-highw
Text Generation • 8B • Updated
• 1
mehuldamani/RLCR-hotpot-tac
Text Generation • 8B • Updated
• 1
mehuldamani/calibration-only-v2
Updated
mehuldamani/RLCR-math-tac
Updated
mehuldamani/RLCR-hotpot-log-loss
Text Generation • 8B • Updated
• 3
mehuldamani/calibration-only
Updated
mehuldamani/RLCR-hotpot-log-loss-v3
Updated
mehuldamani/RLCR-hotpot-normal
Updated