Hugging Face's logo

SaylorTwift
/
lfm-opencode-lora-rl-code

Model card Files
xet
 Community
lfm-opencode-lora-rl-code / train_lora.py

Commit History

14 days ago

  1. Resilient worker (transient CaptureContractError -> unscorable, systematic still fatal), resume-from-repo, eval worker base-cells download fix

    SaylorTwift HF Staff
    Verified signature
    e7168a9

18 days ago

  1. v2: tunnel-free proxy via SPACE_HOST+Jobs expose_public, heartbeat watchdog (30min stall -> fail), keep UploadCheckpointsCallback

    SaylorTwift HF Staff
    Verified signature
    81a1081

19 days ago

  1. Add UploadCheckpointsCallback (transformers v5 removed PushToHubCallback; periodic saves were local-only)

    SaylorTwift HF Staff
    Verified signature
    4e22c33

  2. Set LFM2.5 response_template directly (chat template not recognized by add_response_schema)

    SaylorTwift HF Staff
    Verified signature
    1c2fa85

  3. Pass train_dataset (required by AsyncGRPOTrainer ctor in 1.15.0)

    SaylorTwift HF Staff
    Verified signature
    2a4d2a5

  4. Switch sandboxes to Harbor hf-sandbox backend; add pinned task prep with docker_image patch; dataset discovery via prompt_rows()

    SaylorTwift HF Staff
    Verified signature
    a7525f2

  5. OpenCode-only LoRA RL on LFM2.5-2.6B (verified against trl 1.16.0 / openenv 0.10.0)

    SaylorTwift HF Staff
    Verified signature
    f0273c6