Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
LeTue09
/
arithmetic-grpo
like
0
arxiv:
14 papers
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
arithmetic-grpo
/
verl
/
trainer
/
config
223 kB
Ctrl+K
Ctrl+K
1 contributor
History:
1 commit
LeTue09
initial clean commit
1faccd4
about 2 months ago
actor
initial clean commit
about 2 months ago
algorithm
initial clean commit
about 2 months ago
critic
initial clean commit
about 2 months ago
data
initial clean commit
about 2 months ago
engine
initial clean commit
about 2 months ago
model
initial clean commit
about 2 months ago
model_engine
initial clean commit
about 2 months ago
npu_profile
initial clean commit
about 2 months ago
optim
initial clean commit
about 2 months ago
profiler
initial clean commit
about 2 months ago
ref
initial clean commit
about 2 months ago
reward
initial clean commit
about 2 months ago
rollout
initial clean commit
about 2 months ago
__init__.py
754 Bytes
initial clean commit
about 2 months ago
_generated_ppo_megatron_trainer.yaml
24.4 kB
initial clean commit
about 2 months ago
_generated_ppo_torchtitan_trainer.yaml
21.8 kB
initial clean commit
about 2 months ago
_generated_ppo_trainer.yaml
22.6 kB
initial clean commit
about 2 months ago
_generated_ppo_veomni_trainer.yaml
21 kB
initial clean commit
about 2 months ago
algorithm.py
26.7 kB
initial clean commit
about 2 months ago
config.py
3.75 kB
initial clean commit
about 2 months ago
evaluation.yaml
417 Bytes
initial clean commit
about 2 months ago
legacy_reward_impl.yaml
1.01 kB
initial clean commit
about 2 months ago
ppo_megatron_trainer.yaml
10.1 kB
initial clean commit
about 2 months ago
ppo_trainer.yaml
10 kB
initial clean commit
about 2 months ago
sft_trainer_engine.yaml
4.5 kB
initial clean commit
about 2 months ago