violetxi/exp_rl_all_domains_stage1_qwen8b_grpo
8B • Updated • 4
Violet Xiang PRO
violetxi
AI & ML interests
None yet
Recent Activity
published a model about 5 hours ago
violetxi/qwen3-4b_grpo_alp_b1e-7 updated a dataset about 6 hours ago
violetxi/toolathlon-qwen35-4b-base-pass1-pilot15 published a dataset about 6 hours ago
violetxi/toolathlon-qwen35-4b-base-pass1-pilot15Organizations
violetxi/opsd_medical_qwen3-4b_forward_kl_teacher_step150_lr1e-6
4B • Updated • 4
violetxi/opd_medical_qwen3-4b_forward_kl_teacher_step150_lr1e-6
4B • Updated • 5
violetxi/opd_medical_step1100
Updated
violetxi/grpo_baseline_medical_qwen3-0.6b
0.8B • Updated • 4
violetxi/opd_medical_qwen3-0.6b_frozen_teacher_forward_kl
0.8B • Updated • 6
violetxi/int_qwen3-4b_distill_teacher_reverse_kl_lr1e-7
4B • Updated • 4
violetxi/teacher_grpo_forward_kl-1_16k
4B • Updated • 6
violetxi/teacher_grpo_kl-1_16k
4B • Updated • 3
violetxi/open-thoughts-qwen3-4b-sft1e-6
0.5B • Updated • 6
violetxi/open-thoughts-qwen3-4b-sft
0.5B • Updated • 6
violetxi/qwen3-4b_grpo_alp_b1e-7
4B • Updated