ASIL Qwen3.5-2B SFT
This repository contains the ASIL v0.1.0 paper release checkpoint for ASIL Qwen3.5-2B SFT.
This checkpoint is described in the paper ASIL: Replacing Screenshot-and-Click with Structured State and Semantic Actions.
Project page: https://sharryxr.github.io/ASIL
Code: https://github.com/sharryXR/ASIL
- Release:
v0.1.0 - Selected checkpoint:
global_step_111 - Source path:
/public/home/sjtu_normal/users/xierui/asil_sft_rl_a100_20260513_173133/results/sft_train/qwen35_2b_epoch4_sft_agentic_guided_v2_20260514_190323/checkpoints/global_step_111 - Base/init checkpoint:
/public/home/sjtu_normal/users/xierui/asil_sft_rl_a100_20260513_173133/results/sft_train/qwen35_2b_sft_v0_continue3_20260514_115443/checkpoints/global_step_9 - Training data:
agentic-guided-v2 prepared parquet; 2,330 train / 594 valid rows - Prepared at:
2026-07-30T18:02:32+08:00
The repo root contains the HF-loadable checkpoint files (config.json, tokenizer files, generation_config.json, and *.safetensors). Training-only artifacts such as optimizer state, scheduler state, trainer state, logs, caches, wandb output, and credentials are intentionally excluded.
See checkpoint_metadata.json and SHA256SUMS for provenance and file checksums.