namhokaist/appgen-qwen3-thinktag-lr5e-7-ep1-continue-sft-amex-mobile-use
Continue-SFT of luca0621/appgen-qwen3-thinktag-lr5e-7-ep1 on AMEX-derived GUI trajectories converted to the
mobile_use tool-call format used by AndroidWorld-style mobile agents.
- Base model:
luca0621/appgen-qwen3-thinktag-lr5e-7-ep1 - Output format:
<tool_call>{"name": "mobile_use", "arguments": ...}</tool_call> - Coordinate format: absolute screen pixels
- Qwen3 target format: empty
<think></think>block followed by the tool call - Training data: 38,709 AMEX-derived mobile-use examples
- Training: 1 epoch, lr 5e-7, full SFT, 4x B200, per-device batch 1, gradient accumulation 4, max length 4096, max pixels 2629536
- W&B run: https://wandb.ai/namhokoh-korea-advanced-institute-of-science-and-technology/continue_train_app_gen_b200/runs/hs1idjly
- Downloads last month
- 4
Model tree for namhokaist/appgen-qwen3-thinktag-lr5e-7-ep1-continue-sft-amex-mobile-use
Base model
luca0621/appgen-qwen3-thinktag-lr5e-7-ep1