Racktic/qwen_dedup_top8_dpo_old_math_new_math_syn_olympiads
Updated
Edit Models filters
Showing models from
Tasks
Parameters
Inference Providers
Hardware
Models
12
Active filters: Racktic
Racktic/mix_sft_step800
8B • Updated • 5
Racktic/doc_val
Updated
Racktic/stage1_11k_stage2_11k_mix_step400
8B • Updated • 4
Racktic/stage1_11k_2epoch
8B • Updated • 4
Racktic/stage2_bestrl
8B • Updated • 8
Racktic/stage2_sft554
8B • Updated • 4
Racktic/stage2_qwen_distill_sft
8B • Updated • 5
Racktic/scientist_7b_all_4o_full_toolset_step10
Updated
Racktic/DSGym-models
Updated
Racktic/alchemy-qwen3-ckpt
Updated
Racktic/swecl-qwen35-ckpt
Updated • 1