ColossalAI/applications/ColossalChat/examples/training_scripts
flybird11111 0bc9a870c0
Update train_dpo.py
2024-08-23 13:47:13 +08:00
..
hostfile [FP8] rebase main (#5963) 2024-08-06 16:29:37 +08:00
lora_config.json [FP8] rebase main (#5963) 2024-08-06 16:29:37 +08:00
train_dpo.py Update train_dpo.py 2024-08-23 13:47:13 +08:00
train_dpo.sh [FP8] rebase main (#5963) 2024-08-06 16:29:37 +08:00
train_kto.py [fp8] Merge feature/fp8_comm to main branch of Colossalai (#6016) 2024-08-22 09:21:34 +08:00
train_kto.sh [FP8] rebase main (#5963) 2024-08-06 16:29:37 +08:00
train_orpo.py [fp8] Merge feature/fp8_comm to main branch of Colossalai (#6016) 2024-08-22 09:21:34 +08:00
train_orpo.sh [FP8] rebase main (#5963) 2024-08-06 16:29:37 +08:00
train_ppo.py [fp8] Merge feature/fp8_comm to main branch of Colossalai (#6016) 2024-08-22 09:21:34 +08:00
train_ppo.sh [FP8] rebase main (#5963) 2024-08-06 16:29:37 +08:00
train_rm.py [ColossalChat] Add PP support (#6001) 2024-08-21 10:47:39 +08:00
train_rm.sh [FP8] rebase main (#5963) 2024-08-06 16:29:37 +08:00
train_sft.py [fp8] Merge feature/fp8_comm to main branch of Colossalai (#6016) 2024-08-22 09:21:34 +08:00
train_sft.sh [FP8] rebase main (#5963) 2024-08-06 16:29:37 +08:00