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

LeTue09
/
arithmetic-grpo

Model card Files Files and versions
xet
Community
arithmetic-grpo / tests /special_e2e
94.2 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 1 commit
LeTue09's picture
LeTue09
initial clean commit
1faccd4 29 days ago
  • envs
    initial clean commit 29 days ago
  • generation
    initial clean commit 29 days ago
  • ppo_trainer
    initial clean commit 29 days ago
  • sft
    initial clean commit 29 days ago
  • README.md
    83 Bytes
    initial clean commit 29 days ago
  • __init__.py
    600 Bytes
    initial clean commit 29 days ago
  • check_custom_rwd_fn.py
    1.17 kB
    initial clean commit 29 days ago
  • check_results.py
    1.75 kB
    initial clean commit 29 days ago
  • run_dapo.sh
    3.55 kB
    initial clean commit 29 days ago
  • run_fully_async_policy.sh
    8.12 kB
    initial clean commit 29 days ago
  • run_geo3k_fsdp_sgl_multiturn_w_tool.sh
    2.61 kB
    initial clean commit 29 days ago
  • run_grpo_lora_with_merge.sh
    3.59 kB
    initial clean commit 29 days ago
  • run_gsm8k_fsdp_sgl_multiturn_sf_tool.sh
    2.52 kB
    initial clean commit 29 days ago
  • run_gsm8k_fsdp_sgl_multiturn_w_tool.sh
    2.6 kB
    initial clean commit 29 days ago
  • run_one_step_off_policy.sh
    7.56 kB
    initial clean commit 29 days ago
  • run_ppo_trainer_megatron.sh
    13.1 kB
    initial clean commit 29 days ago
  • run_ppo_trainer_torchtitan.sh
    3.18 kB
    initial clean commit 29 days ago
  • run_ppo_trainer_veomni.sh
    3.06 kB
    initial clean commit 29 days ago
  • run_test.sh
    359 Bytes
    initial clean commit 29 days ago