github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2026-04-11 14:43:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

[pre-commit.ci] auto fixes from pre-commit.com hooks

Browse Source 
for more information, see https://pre-commit.ci
This commit is contained in:
pre-commit-ci[bot]
2025-08-14 11:05:40 +00:00
parent 99ba48fc40
commit 73bdfd8891
5 changed files with 10 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
applications/ColossalChat/examples/training_scripts/train_grpo.py
View File

@@ -89,9 +89,7 @@ def train(args):
actor = AutoModelForCausalLM.from_pretrained(args.pretrain, trust_remote_code=True)
if args.rm_pretrain:
reward_model = RewardModel(args.rm_pretrain, trust_remote_code=True)
ref_model = AutoModelForCausalLM.from_pretrained(
args.pretrain, trust_remote_code=True
)
ref_model = AutoModelForCausalLM.from_pretrained(args.pretrain, trust_remote_code=True)
if args.lora_config is not None:
actor = convert_to_lora_module(actor, lora_config=lora_config)

4
applications/ColossalChat/examples/training_scripts/train_ppo.py
View File

@@ -102,9 +102,7 @@ def train(args):
coordinator.print_on_master(msg="Flash-attention enabled successfully")
else:
actor = AutoModelForCausalLM.from_pretrained(args.pretrain, trust_remote_code=True)
ref_model = AutoModelForCausalLM.from_pretrained(
args.pretrain, trust_remote_code=True
)
ref_model = AutoModelForCausalLM.from_pretrained(args.pretrain, trust_remote_code=True)
if not args.no_neural_reward_model:
reward_model = RewardModel(args.rm_pretrain, trust_remote_code=True)
critic = Critic(args.rm_pretrain)