t2ance/smoke-domain
Updated
👋 Open to Work
Peijia Qin
t2ance
AI & ML interests
None yet
Recent Activity
updated a dataset about 22 hours ago
t2ance/OnlineGRPO-Selection-Domain-1.7B published a dataset about 22 hours ago
t2ance/OnlineGRPO-Selection-Domain-1.7B updated a model about 23 hours ago
t2ance/smoke-domainOrganizations
models 95
t2ance/atlas-ppo_qwen3_8b_pattern_gpqa_overall_utility_prefix_potential_lora_2gpu
Updated
t2ance/atlas-tcp2ae6x_step40_merged
8B • Updated • 16
t2ance/atlas-sft_qwen3_8b_pattern_teacher_merged
8B • Updated • 15 • 1
t2ance/atlas-sft_qwen3_8b_pattern_teacher_lcb_merged
8B • Updated • 16 • 1
t2ance/atlas-sft_qwen3_8b_pattern_teacher_lcb
Text Generation • Updated • 30
t2ance/atlas-sft_qwen3_8b_pattern_teacher_gpqa_merged
8B • Updated • 18 • 1
t2ance/atlas-sft_qwen3_8b_pattern_teacher_gpqa_firstcall_noconf_merged
8B • Updated • 16
t2ance/atlas-sft_qwen3_8b_pattern_teacher_gpqa_firstcall_noconf
Text Generation • Updated • 33
t2ance/atlas-sft_qwen3_8b_pattern_teacher_gpqa_firstcall_merged_grpo_step40
8B • Updated • 16 • 1
datasets 51
t2ance/OnlineGRPO-Selection-Domain-1.7B
Viewer • Updated • 786
t2ance/atlas-32-turn-level-actor-critic
Preview • Updated • 5.65k
t2ance/atlas-35-joint-math-and-code-training-data
Updated • 2.23k
t2ance/atlas-31-strengthening-candidate-verification-under-rl
Preview • Updated • 2.44k
t2ance/atlas-30-openmathreasoning-genselect-training
Preview • Updated • 4.31k
t2ance/atlas-34-trained-orchestrators-under-the-paper-protocol
Updated • 10
t2ance/atlas-29-supergpqa-records-as-a-candidate-pool
Preview • Updated • 58
t2ance/atlas-28-explore-cost-in-dollars
Updated • 553
t2ance/atlas-25-sequential-tool-runtime-upgrade
Viewer • Updated • 197 • 1.5k
t2ance/atlas-04-update-dose-and-entropy-collapse
Updated • 299