Hugging Face's logo

armand0e
/
test-1-lora

PEFT
Safetensors
lora
grpo
dpo
experimental
Model card Files
xet
 Community
test-1-lora

Commit History

6 days ago

  1. main: GRPO189 + DPO117 (last trained adapter) and project write-up

    armand0e
    Verified signature
    e1a7af9

7 days ago

  1. Latest testing adapter: GRPO189 plus broad DPO54; mixed evaluation results · verified cumulative adapter 1ce449c0e3db

    armand0e
    Verified signature
    2e4bacd

  2. MiMo preview baseline: GRPO189 plus DPO62, before SFT and later RL · verified cumulative adapter 7cf1c85a6047

    armand0e
    Verified signature
    727a696

  3. MiMo preview: latest completed SFT96 plus RL8 cumulative adapter · verified cumulative adapter d1ed9c035c45

    armand0e
    Verified signature
    9832326

  4. Upload combined GRPO189 + DPO62 preview LoRA

    armand0e
    Verified signature
    7837660

10 days ago

  1. GRPO step 171 LoRA adapter (replaces step 115)

    armand0e
    Verified signature
    211331f

25 days ago

  1. GRPO step 115 LoRA adapter (re-run from step 100, lr 1e-5; replaces step 110)

    armand0e
    Verified signature
    2f875c9

27 days ago

  1. GRPO step 110 LoRA adapter (replaces step 75)

    armand0e
    Verified signature
    47356c1

30 days ago

  1. Replace with GRPO step 75 LoRA adapter

    armand0e
    Verified signature
    3241f4f

  1. Replace with GRPO step 52 LoRA adapter

    armand0e
    Verified signature
    540e6c6

  1. Replace with GRPO step 45 LoRA adapter

    armand0e
    Verified signature
    d7714d5

  1. MiMo-V2.6-Distill-Qwen-9B GRPO step 25 LoRA adapter (best validation checkpoint)

    armand0e
    Verified signature
    82cd5e0

  2. initial commit

    armand0e
    Verified signature
    02523bd