Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
tahamajs
/
AsyncTensorRLHF
Like
0
Reinforcement Learning
PyTorch
English
rlhf
ppo
grpo
m2po
vllm
async
cuda
tensor-native
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
AsyncTensorRLHF
/
src
/
trainer
7.16 kB
Ctrl+K
Ctrl+K
1 contributor
History:
1 commit
tahamajs
Initial release of AsyncTensorRLHF: High-Throughput Asynchronous RLHF with Tensor-Native Rewards
e791b16
verified
12 days ago
__init__.py
30 Bytes
Initial release of AsyncTensorRLHF: High-Throughput Asynchronous RLHF with Tensor-Native Rewards
12 days ago
grpo_loss.py
875 Bytes
Initial release of AsyncTensorRLHF: High-Throughput Asynchronous RLHF with Tensor-Native Rewards
12 days ago
ppo_loss.py
2.2 kB
Initial release of AsyncTensorRLHF: High-Throughput Asynchronous RLHF with Tensor-Native Rewards
12 days ago
trainer_worker.py
4.06 kB
Initial release of AsyncTensorRLHF: High-Throughput Asynchronous RLHF with Tensor-Native Rewards
12 days ago
