·
AI & ML interests
None yet
Organizations
1231czx/kl001_numia_dpo_iter5
Text Generation
• 8B • Updated
1231czx/qwen_self_corr_warmup_packed_2ep
Text Generation
• 8B • Updated
• 1
1231czx/kl001_numia_dpo_iter4
Text Generation
• 8B • Updated
1231czx/kl001_numia_dpo_iter3
Text Generation
• 8B • Updated
1231czx/kl001_numia_dpo_iter2
Text Generation
• 8B • Updated
1231czx/kl001_numia_dpo_iter1
Text Generation
• 8B • Updated
1231czx/new_script_qwq_warmup_15k_iter2_dpo_iter6
Text Generation
• 8B • Updated
1231czx/new_script_qwq_warmup_15k_iter2_dpo_iter5
Text Generation
• 8B • Updated
1231czx/new_script_qwq_warmup_15k_iter2_dpo_iter4
Text Generation
• 8B • Updated
1231czx/new_script_qwq_warmup_15k_iter2_dpo_iter3
Text Generation
• 8B • Updated
1231czx/new_script_qwq_warmup_15k_iter2_dpo_iter2
Text Generation
• 8B • Updated
1231czx/new_script_qwq_warmup_15k_iter2_dpo_iter1
Text Generation
• 8B • Updated
1231czx/new_script_qwq_warmup_15k_iter3
Text Generation
• 8B • Updated
1231czx/new_script_qwq_warmup_15k_iter1
Text Generation
• 8B • Updated
1231czx/new_script_qwq_warmup_15k_iter2
Text Generation
• 8B • Updated
Text Classification
• 8B • Updated
• 1
1231czx/aug_math_llama3_8b_packed_lr2e6_2ep
Text Generation
• 8B • Updated
1231czx/aug_math_llama3_8b_packed_lr3e6_2ep
Text Generation
• 8B • Updated
1231czx/aug_math_llama3_8b_packed_lr5e6_2ep
Text Generation
• 8B • Updated
1231czx/llama31_it_orm_1e6_bz128_dsdata
Text Classification
• 8B • Updated
• 1
1231czx/llama31_it_orm_1e6_bz128_msdata
Text Classification
• 8B • Updated
• 2
1231czx/ver2_step_wise_dpo_bz64_step400
Text Generation
• 7B • Updated
1231czx/ver2_step_wise_dpo_bz64_step300
Text Generation
• 7B • Updated
1231czx/ver2_step_wise_dpo_bz64_step200
Text Generation
• 7B • Updated
1231czx/ver2_step_wise_dpo_bz64_step100
Text Generation
• 7B • Updated
Text Generation
• 266k • Updated
• 6
1231czx/he_random_lm_head_llama31_it
Text Generation
• 8B • Updated
1231czx/random_lm_head_llama31_it
Text Generation
• 8B • Updated
• 1
1231czx/step_wise_dpo_bz64_step900
Text Generation
• 7B • Updated
1231czx/step_wise_dpo_bz64_step800
Text Generation
• 7B • Updated