Hugging Face's logo

Alogotron
/
a0-toolcall-lora

PEFT
Safetensors
English
agent-zero
tool-calling
qlora
lora
function-calling
sft
Model card Files
xet
 Community
a0-toolcall-lora

Commit History

  1. fix: add adapter_config.json required for PEFT loading

    Alogotron
    Verified signature
    c7a1db5

  2. feat: QLoRA adapter weights - Qwen2.5-7B-Instruct A0 tool-call tune (r16, 40.4M trainable)

    Alogotron
    Verified signature
    c1c2472

  3. docs: model card with measured base-vs-tuned numbers

    Alogotron
    Verified signature
    3bbcb15

  4. feat: eval results - validity 1.7%->84.7%, invalid 58->0, stall analysis (512-cap)

    Alogotron
    Verified signature
    a1f920c

  5. initial commit

    Alogotron
    Verified signature
    3068328