| { | |
| "feature_size": 512, | |
| "n_layers": 5, | |
| "gpt_config": { | |
| "name": "ascii_64x4", | |
| "device": "cuda", | |
| "compile": true, | |
| "block_size": 128, | |
| "vocab_size": 128, | |
| "n_layer": 4, | |
| "n_head": 4, | |
| "n_embd": 64 | |
| }, | |
| "l1_coefficient": [ | |
| 0.02, | |
| 0.06, | |
| 0.2, | |
| 0.2, | |
| 0.5 | |
| ] | |
| } |
| { | |
| "feature_size": 512, | |
| "n_layers": 5, | |
| "gpt_config": { | |
| "name": "ascii_64x4", | |
| "device": "cuda", | |
| "compile": true, | |
| "block_size": 128, | |
| "vocab_size": 128, | |
| "n_layer": 4, | |
| "n_head": 4, | |
| "n_embd": 64 | |
| }, | |
| "l1_coefficient": [ | |
| 0.02, | |
| 0.06, | |
| 0.2, | |
| 0.2, | |
| 0.5 | |
| ] | |
| } |