| { | |
| "model_type": "multiscale_transformer", | |
| "architectures": [ | |
| "MultiScaleForCausalLM" | |
| ], | |
| "vocab_size": 258, | |
| "d_model": 224, | |
| "n_heads": 4, | |
| "d_ff": 608, | |
| "n_layers_per_scale": 3, | |
| "n_cross_attn_layers": 1, | |
| "max_seq_len": 512, | |
| "dropout": 0.0, | |
| "bias": false, | |
| "rope_theta": 10000.0, | |
| "downsample_factors": [ | |
| 1, | |
| 2, | |
| 4 | |
| ], | |
| "num_parameters": 9259040, | |
| "training_results": { | |
| "model": "AXL-Chat-10M", | |
| "params": 9870112, | |
| "steps": 501, | |
| "time": 180.17745065689087, | |
| "final_loss": 0.005268150940537453, | |
| "perplexity": 1.02, | |
| "max_seq_len": 512, | |
| "context_window": "512 bytes" | |
| } | |
| } |