·
AI & ML interests
None yet
Organizations
fengyao1909/full_base_gsm_bs32_lr1e-5_zero3_ckpt35
31B • Updated • 2
fengyao1909/full_base_s1k_bs16_lr1e-5_zero3_ckpt189
31B • Updated • 3
fengyao1909/full_base_s1k_bs16_lr1e-5_zero3_ckpt252
31B • Updated fengyao1909/full_base_s1k_bs16_lr1e-5_zero3_ckpt315
31B • Updated • 1
fengyao1909/full_base_s1k_bs16_lr1e-5_zero3_final
Text Generation
• 31B • Updated • 5
fengyao1909/ste_base_s1k_bs16_lr1e-5_zero3_final
Text Generation
• 31B • Updated • 2
fengyao1909/ste_base_s1k_bs16_lr1e-5_zero3_ckpt315
31B • Updated • 1
fengyao1909/ste_base_s1k_bs16_lr1e-5_zero3_ckpt252
31B • Updated • 1
fengyao1909/ste_base_s1k_bs16_lr1e-5_zero3_ckpt189
31B • Updated • 1
fengyao1909/ste_base_alpacafarm_bs32_lr1e-5_zero3
31B • Updated • 1
fengyao1909/base_alpacafarm_bs32_lr1e-5_zero3
31B • Updated • 1
fengyao1909/qwen30b_alpacafarm_bs64
31B • Updated • 2
fengyao1909/qwen30b_alpacafarm_bs32
31B • Updated • 1
Text Generation
• 8B • Updated • 2
Text Generation
• 3B • Updated • 2
Text Generation
• 0.5B • Updated • 3
fengyao1909/rmx1.0_tau1.0_lr3e-6_klold5_klref0.05_fs_ir
Updated
fengyao1909/rmx1.0_tau1.0_lr3e-6_klold5_klref0.05_fs_noir
Updated
Text Generation
• 1B • Updated • 1
fengyao1909/purplellama_h100_step135
0.6B • Updated • 1
fengyao1909/phi-2-franken
Text Generation
• 5B • Updated • 1