Hugging Face's logo

chomeed
/
robometer-4b-full-threading-d0

Transformers
Safetensors
qwen2_5_vl
reward_model
rbm
robometer
mimicgen
text-generation-inference
Model card Files
xet
 Community
robometer-4b-full-threading-d0 / README.md

Commit History

  1. Model card: full FT vs LoRA results, autocast caveat, repro command

    chomeed
    Verified signature
    72fb392

  2. Full fine-tune of Robometer-4B on mimicgen threading_d0 (best ckpt, step 500)

    chomeed
    Verified signature
    8e0d74a