Racktic/stage2_qwen_distill_sft
8B
•
Updated
•
6
XuQixin
Racktic
AI & ML interests
NLP, mutimodel
Recent Activity
updated
a dataset
3 days ago
Racktic/doc_val_outputs
updated
a dataset
4 days ago
Racktic/ablation_nosyndata_logs
published
a dataset
4 days ago
Racktic/ablation_nosyndata_logs
Organizations
None yet
Racktic/stage2_sft554
8B
•
Updated
•
9
Racktic/stage2_bestrl
8B
•
Updated
•
9
Racktic/stage1_11k_2epoch
8B
•
Updated
•
6
Racktic/stage1_11k_stage2_11k_mix_step400
8B
•
Updated
•
11
Racktic/doc_val
Updated
Racktic/mix_sft_step800
8B
•
Updated
•
11
Racktic/qwen_dedup_top8_dpo_old_math_new_math_syn_olympiads
Updated