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
Spaces:
yashvyasop
/
DesignGym
like
1
Running
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
DesignGym
/
training
115 kB
Ctrl+K
Ctrl+K
1 contributor
History:
34 commits
yashvyasop
grpo: add --eval_best_of (best-of-N eval for SFT and GRPO)
8a2235b
verified
22 days ago
generate_sft_data.py
Safe
17.7 kB
Upload folder using huggingface_hub
23 days ago
grpo_train.py
Safe
57.8 kB
grpo: add --eval_best_of (best-of-N eval for SFT and GRPO)
22 days ago
grpo_train_colab.ipynb
Safe
13 kB
Colab: HF Jobs orchestrator (full 400/200/3 run)
23 days ago
run_grpo.sh
Safe
4.73 kB
grpo: add --eval_best_of (best-of-N eval for SFT and GRPO)
22 days ago
run_grpo_smoke_job.sh
Safe
1.78 kB
Fix GRPO smoke dependencies with llm-blender
23 days ago
train_grpo_designgym2.py
Safe
19.6 kB
Fix GRPO training script import path
23 days ago
