Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • 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

JaehaL
/
bgrpo-tmlr-models

Reinforcement Learning
PyTorch
Transformers
grpo
symbolic-mathematics
polynomial-decomposition
Model card Files Files and versions
xet
Community

Instructions to use JaehaL/bgrpo-tmlr-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use JaehaL/bgrpo-tmlr-models with Transformers:

    # pip install -U transformers accelerate
    # Load model directly
    from transformers import AutoModel
    model = AutoModel.from_pretrained("JaehaL/bgrpo-tmlr-models", device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
bgrpo-tmlr-models / sft_base
324 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 1 commit
JaehaL's picture
JaehaL
BGRPO TMLR paper models: 3 SFT bases + 27 RL endpoints (step 420)
2033b02 verified about 1 month ago
  • d2_arch_256_l6_snapshot_best.pt
    37.6 MB
    xet
    BGRPO TMLR paper models: 3 SFT bases + 27 RL endpoints (step 420) about 1 month ago
  • d2_arch_512r3_l6_snapshot_best.pt
    95.5 MB
    xet
    BGRPO TMLR paper models: 3 SFT bases + 27 RL endpoints (step 420) about 1 month ago
  • d2_arch_768r2_l6_snapshot_best.pt
    191 MB
    xet
    BGRPO TMLR paper models: 3 SFT bases + 27 RL endpoints (step 420) about 1 month ago