Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Spaces:
iteratehack
/
deepbattler
like
1
Sleeping
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
deepbattler
/
RL
532 kB
2 contributors
History:
3 commits
lbtwyk
Update README to focus on RL training pipeline
fed1ca7
12 days ago
eval_battleground_rlaif.py
Safe
22.8 kB
Upload folder using huggingface_hub
12 days ago
eval_battleground_rlaif_gamehistory.py
Safe
25.6 kB
Upload folder using huggingface_hub
12 days ago
eval_gsm8k_qwen.py
Safe
27.8 kB
Upload folder using huggingface_hub
12 days ago
flatten_game_history.py
Safe
5.71 kB
Upload folder using huggingface_hub
12 days ago
gsm8k_test.json
Safe
381 kB
Upload folder using huggingface_hub
12 days ago
infer_battleground_cloud.py
Safe
11.8 kB
Update README to focus on RL training pipeline
12 days ago
rewrite_battleground_rewards.py
Safe
1.99 kB
Upload folder using huggingface_hub
12 days ago
train_battleground_rlaif.py
Safe
17.8 kB
Upload folder using huggingface_hub
12 days ago
train_battleground_rlaif_gamehistory.py
Safe
25.6 kB
Upload folder using huggingface_hub
12 days ago
train_gsm8k_qwen_grpo.py
Safe
12.7 kB
Upload folder using huggingface_hub
12 days ago