Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Posts
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

zeju-0727
/
Dyve_plus_RL_copy

Model card Files Files and versions Community
Dyve_plus_RL_copy
Ctrl+K
Ctrl+K
  • 1 contributor
History: 8 commits
zeju-0727's picture
zeju-0727
Upload grpo_train.py with huggingface_hub
5cad8b7 verified 2 months ago
  • .gitattributes
    1.59 kB
    Upload 0312_training_new_processed_16w.jsonl with huggingface_hub 2 months ago
  • 0312_training_new_processed_16w.jsonl
    1.58 GB
    LFS
    Upload 0312_training_new_processed_16w.jsonl with huggingface_hub 2 months ago
  • grpo_train.py
    16.6 kB
    Upload grpo_train.py with huggingface_hub 2 months ago
  • llm_as_judge.py
    4.96 kB
    Upload llm_as_judge.py with huggingface_hub 2 months ago
  • llm_rewash_data.py
    5.03 kB
    Upload llm_rewash_data.py with huggingface_hub 2 months ago
  • requirements.txt
    234 Bytes
    Upload requirements.txt with huggingface_hub 2 months ago
  • run_vllm_LM.sh
    328 Bytes
    Upload run_vllm_LM.sh with huggingface_hub 2 months ago