·
AI & ML interests
None yet
Organizations
None yet
saurabh5/code_rlvr_mixture_dpo
Viewer • Updated • 21.3k • 28
Viewer • Updated • 214 • 5
saurabh5/hard-coded-olmo-qwen3-vl-32b-thinking-traces-hand-filtered
Viewer • Updated • 58 • 7
saurabh5/hard-coded-olmo-qwen3-vl-32b-thinking-traces
Viewer • Updated • 60 • 14
saurabh5/hard-coded-olmo-DPO-qwen3-vl-32b-thinking
Viewer • Updated • 168 • 2
saurabh5/hard-coded-olmo-DPO-qwen3-vl-32b-instruct
Viewer • Updated • 168 • 11
saurabh5/hard-coded-olmo-qwq-32b-traces
Viewer • Updated • 60 • 7
saurabh5/coding-agent-synth-data
Viewer • Updated • 8.09k • 12
saurabh5/RL0-General-Data
Viewer • Updated • 12.8k • 17
Viewer • Updated • 13.2k • 8
Viewer • Updated • 13.3k • 1
Viewer • Updated • 13.3k • 6
saurabh5/olmo3-7B-RL0-mix
Viewer • Updated • 46.8k • 15
saurabh5/synthetic2-rlvr-code-compressed
Viewer • Updated • 11.1k • 12
Viewer • Updated • 15k • 19
saurabh5/MATH_3000_Filtered_olmo_completions_new_template_filtered
Viewer • Updated • 2.93k • 11
saurabh5/DAPO-Math-17k-Processed_filtered_olmo_completions_new_template_filtered
Viewer • Updated • 10.4k • 10
saurabh5/MATH_3000_Filtered_olmo_completions_new_template
Viewer • Updated • 3k • 5
saurabh5/DAPO-Math-17k-Processed_filtered_olmo_completions_new_template
Viewer • Updated • 12.6k • 10
saurabh5/IF_multi_constraints_upto5_filtered_olmo_completions_filtered
Viewer • Updated • 88.6k • 67
saurabh5/rlvr_acecoder_filtered_filtered_olmo_completions_filtered
Viewer • Updated • 62.5k • 14
saurabh5/synthetic2-rlvr-code-compressed_filtered_olmo_completions_filtered
Viewer • Updated • 10.9k • 5
saurabh5/DAPO-Math-17k-Processed_filtered_olmo_completions_filtered
Viewer • Updated • 12.6k • 13
saurabh5/MATH_3000_Filtered_olmo_completions_filtered
Viewer • Updated • 3k • 5
saurabh5/MATH_3000_Filtered_olmo_completions
Viewer • Updated • 3k • 22
saurabh5/DAPO-Math-17k-Processed_filtered_olmo_completions
Viewer • Updated • 12.6k • 7
saurabh5/synthetic2-rlvr-code-compressed_filtered_olmo_completions
Viewer • Updated • 11k • 11
saurabh5/rlvr_acecoder_filtered_filtered_olmo_completions
Viewer • Updated • 62.8k • 10
saurabh5/IF_multi_constraints_upto5_filtered_olmo_completions
Viewer • Updated • 95.3k • 19
saurabh5/rlvr-code-view-tool-new-first-turn-only-user-with-repo-name
Viewer • Updated • 13.3k • 10