| { | |
| "model": "Qwen/Qwen2.5-1.5B-Instruct", | |
| "d_model": 1536, | |
| "num_layers": 28, | |
| "num_heads": 12, | |
| "inject_layer": 9, | |
| "best_lambda": 1.0, | |
| "n_incontext": 4, | |
| "n_target_prompts": 15, | |
| "top_heads": [ | |
| { | |
| "layer": 24, | |
| "head": 3, | |
| "aie": 0.004586321767419577 | |
| }, | |
| { | |
| "layer": 20, | |
| "head": 9, | |
| "aie": 0.0027352971956133842 | |
| }, | |
| { | |
| "layer": 0, | |
| "head": 6, | |
| "aie": 0.0017912477487698197 | |
| }, | |
| { | |
| "layer": 17, | |
| "head": 7, | |
| "aie": 0.0017713563283905387 | |
| }, | |
| { | |
| "layer": 20, | |
| "head": 8, | |
| "aie": 0.0016093882732093334 | |
| }, | |
| { | |
| "layer": 21, | |
| "head": 3, | |
| "aie": 0.0014112978242337704 | |
| }, | |
| { | |
| "layer": 18, | |
| "head": 10, | |
| "aie": 0.001295118359848857 | |
| }, | |
| { | |
| "layer": 17, | |
| "head": 3, | |
| "aie": 0.0012491021770983934 | |
| }, | |
| { | |
| "layer": 15, | |
| "head": 1, | |
| "aie": 0.00092243158724159 | |
| }, | |
| { | |
| "layer": 19, | |
| "head": 11, | |
| "aie": 0.0007095862529240549 | |
| } | |
| ], | |
| "sampling_strategy": "Indices 0-29 used as validation (lambda tuning). Indices 30-44 as target queries. Indices 45+ as in-context pool. N=4 in-context examples per prompt, sampled without replacement." | |
| } |