Hugging Face's logo 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

yashash045
/
devops-pipeline-gym-trained

Transformers
Safetensors
Generated from Trainer
trl
grpo
hf_jobs
Model card Files Files and versions
xet
Metrics Training metrics Community

Instructions to use yashash045/devops-pipeline-gym-trained with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use yashash045/devops-pipeline-gym-trained with Transformers:

    # Load model directly
    from transformers import AutoModel
    model = AutoModel.from_pretrained("yashash045/devops-pipeline-gym-trained", dtype="auto")
  • Notebooks
  • Google Colab
  • Kaggle
devops-pipeline-gym-trained / final
116 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
yashash045's picture
yashash045
GRPO retry: 300 steps from SFT, num_gen=16, max_comp_len=512
42f8547 verified 29 days ago
  • ref
    GRPO retry: 300 steps from SFT, num_gen=16, max_comp_len=512 29 days ago
  • README.md
    5.22 kB
    Phase M Stage 2: GRPO 200 steps adapter + training logs (logs/, grpo_log.csv, curriculum_progress.jsonl, reward_curve.png) 29 days ago
  • adapter_config.json
    1.19 kB
    GRPO retry: 300 steps from SFT, num_gen=16, max_comp_len=512 29 days ago
  • adapter_model.safetensors
    34.9 MB
    xet
    GRPO retry: 300 steps from SFT, num_gen=16, max_comp_len=512 29 days ago
  • chat_template.jinja
    4.67 kB
    Phase M Stage 2: GRPO 200 steps adapter + training logs (logs/, grpo_log.csv, curriculum_progress.jsonl, reward_curve.png) 29 days ago
  • tokenizer.json
    11.4 MB
    xet
    Phase M Stage 2: GRPO 200 steps adapter + training logs (logs/, grpo_log.csv, curriculum_progress.jsonl, reward_curve.png) 29 days ago
  • tokenizer_config.json
    404 Bytes
    Phase M Stage 2: GRPO 200 steps adapter + training logs (logs/, grpo_log.csv, curriculum_progress.jsonl, reward_curve.png) 29 days ago