·
AI & ML interests
None yet
Organizations
1231czx/qwmathbase_reinforce40
8B • Updated
• 1
1231czx/qwmathbase_reinforce20
8B • Updated
• 1
1231czx/qwmathbase_raftpp_bz512_n8_step260
8B • Updated
• 1
1231czx/qwmathbase_raftpp_bz512_n8_step240
8B • Updated
• 1
1231czx/qwmathbase_raftpp_bz512_n8_step220
8B • Updated
1231czx/qwmathbase_raftpp_bz512_n8_step200
8B • Updated
1231czx/llama_32_3b_it_ppo_step220
4B • Updated
1231czx/llama_32_3b_it_ppo_step200
4B • Updated
• 1
1231czx/llama_32_3b_it_ppo_step180
4B • Updated
• 1
1231czx/llama_32_3b_it_ppo_step160
4B • Updated
1231czx/llama_32_3b_it_ppo_step140
4B • Updated
• 1
1231czx/llama_32_3b_it_ppo_step120
4B • Updated
• 1
1231czx/llama_32_3b_it_ppo_step100
4B • Updated
• 2
1231czx/llama_32_3b_it_ppo_step80
4B • Updated
1231czx/llama_32_3b_it_ppo_step60
4B • Updated
1231czx/llama_32_3b_it_ppo_step40
4B • Updated
• 1
1231czx/llama_32_3b_it_ppo_step20
4B • Updated
• 1
1231czx/qwmathbase_raftpp_bz512_n8_step180
8B • Updated
• 1
1231czx/qwmathbase_raftpp_bz512_n8_step160
8B • Updated
• 1
1231czx/qwmathbase_raftpp_bz512_n8_step140
8B • Updated
• 1
1231czx/qwmathbase_raftpp_bz512_n8_step120
8B • Updated
• 2
1231czx/qwmathbase_grpo2_step340
8B • Updated
• 2
1231czx/qwmathbase_grpo2_step320
8B • Updated
• 1
1231czx/qwmathbase_grpo2_step300
8B • Updated
• 1
1231czx/qwmathbase_grpo2_step280
8B • Updated
• 2
1231czx/qwmathbase_grpo2_step260
8B • Updated
• 1
1231czx/qwmathbase_grpo2_step240
8B • Updated
• 1
1231czx/qwmathbase_raftpp_bz512_n8_step100
8B • Updated
• 1
1231czx/qwmathbase_raftpp_bz512_n8_step80
8B • Updated
• 1
1231czx/qwmathbase_raftpp_bz512_n8_step60
8B • Updated