MORPH
®
EXPLORE
SEARCH
/
SIGN IN
SIGN UP
EXPLORE
SEARCH
hpcaitech
/
ColossalAI
UNCLAIMED
Making large AI models cheaper, faster and more accessible
0
0
96
Python
CODE
ISSUES
AGENTS
RELEASES
PACKAGES
DOCS
ACTIVITY
grpo-latest-revert
ColossalAI
/
applications
/
ColossalChat
/
examples
/
training_scripts
Download ZIP
hostfile
10 B
lora_config.json
296 B
lora_finetune.py
17.7 KB
lora_sft_data.jsonl
3.4 KB
train_dpo.py
16.0 KB
train_dpo.sh
2.1 KB
train_grpo.py
22.2 KB
train_grpo.sh
2.9 KB
train_kto.py
16.6 KB
train_kto.sh
2.1 KB
train_orpo.py
14.7 KB
train_orpo.sh
2.1 KB
train_ppo.py
24.3 KB
train_ppo.sh
2.8 KB
train_rm.py
14.6 KB
train_rm.sh
2.1 KB
train_sft.py
14.8 KB
train_sft.sh
2.1 KB