| # Edit-agent configuration (dialogue SFT + later bridge stages) | |
| paths: | |
| dataset_jsonl: data/edit_dataset/manifests/dataset.jsonl | |
| dialogues_jsonl: data/edit_dataset/dialogues/dialogues.jsonl | |
| bridge_cache_dir: data/edit_dataset/bridge_cache | |
| ckpt_root: ckpts/edit_agent | |
| tokens: | |
| k_edit: 8 | |
| qwen: | |
| model_id: Qwen/Qwen2.5-Omni-7B | |
| attn: sdpa | |
| dtype: bf16 | |
| sft: | |
| lora: {r: 16, alpha: 32, dropout: 0.05} | |
| lr: 1.0e-4 | |
| batch: 1 | |
| grad_accum: 16 | |
| epochs: 2 | |
| warmup: 300 | |
| log_every: 10 | |
| save_every: 500 | |
| # Stage A (bridge) — filled in when that stage is implemented | |
| bridge: | |
| d_llm: 3584 | |
| dit_dim: 2048 | |
| cross_attn_layers: [0, 2, 4, 6, 8, 10, 12, 14] | |
| lora: {r: 16, alpha: 32} | |
| drops: {edit_cond: 0.1, src_cond: 0.1} | |
| loss_w: {flow: 1.0, align: 1.0, nce: 0.5} | |