mehuldamani/sft-qwen-vmaze-v1
Text Generation • 3B • Updated • 278
Mehul Damani PRO
mehuldamani
AI & ML interests
Reinforcement Learning, Large Language Models
Recent Activity
updated a model about 22 hours ago
mehuldamani/sft-qwen-vmaze-v1 published a model about 22 hours ago
mehuldamani/sft-qwen-vmaze-v1 published a model 1 day ago
mehuldamani/rlvr_multi_k3Organizations
None yet
mehuldamani/rlvr_multi_k3
Updated
mehuldamani/rlvr_single
Updated
mehuldamani/qwen3_8b_medical_rlcr_multi_k_4
Updated
mehuldamani/qwen3_8b_medical_rlcr_multi_k_2
Updated
mehuldamani/qwen3_8b_medical_rlcr_multi_k_5
Updated
mehuldamani/sft-qwen-maze-v2
Text Generation • 8B • Updated • 83
mehuldamani/sft-qwen-maze-v1
Text Generation • 8B • Updated • 658
mehuldamani/sft-maze-v2
Text Generation • 8B • Updated • 380
mehuldamani/partial-sft-story-v6
Text Generation • 8B • Updated • 153
mehuldamani/instruct-story-v6
Text Generation • 8B • Updated • 200
mehuldamani/sft-new-story-v4
Text Generation • 8B • Updated • 454
mehuldamani/sft-mini-story
Text Generation • 8B • Updated • 324
mehuldamani/sft-new-story-v3
Text Generation • 8B • Updated • 667
mehuldamani/sft-new-story-v1
Text Generation • 8B • Updated • 241
mehuldamani/sft-story-v1
Text Generation • 8B • Updated • 25
mehuldamani/qwen25noInstruct_rlvr_multi_veryHardDataset_mediumThinking
Updated
mehuldamani/again_qwen25noInstruct_SFTed_rlvr_multi_veryHardDataset_moreThinking_biggerBatchSmallrLR
Updated
mehuldamani/again_qwen25noInstruct_SFTed_rlvr_multi_veryHardDataset_moreThinking
Updated
mehuldamani/rlcr_multi_fromRLVR_multi_moreThinking
Updated
mehuldamani/rlcr_multi_fromRLVR_multi
Updated
mehuldamani/rlcr_single_fromRLVRSingle
Updated
mehuldamani/Instruct-SFT-Classifier-v1
Text Classification • 8B • Updated • 232
mehuldamani/qwen25_base_rlcr_multi_noSFT_withAnalysis_veryHardDataset
Updated
mehuldamani/qwen25_base_rlcr_single_mehulSFTed_veryHardDataset
Updated
mehuldamani/sft-instruct-vvx2
Text Generation • 8B • Updated • 1.88k
mehuldamani/qwen25_base_rlcr_single_noSFT_veryHardDataset
Updated
mehuldamani/qwen25_base_rlcr_multi_noSFT_veryHardDataset
Updated
mehuldamani/Llama-3.1-8B-Instruct-modified
Text Generation • 8B • Updated • 395
mehuldamani/qwen25noInstruct_rlvr_multi_veryHardDataset_moreThinking
Updated