config.json

{
  "model_type": "multiscale_transformer",
  "architectures": [
    "MultiScaleForCausalLM"
  ],
  "vocab_size": 258,
  "d_model": 256,
  "n_heads": 4,
  "d_ff": 688,
  "n_layers_per_scale": 4,
  "n_cross_attn_layers": 1,
  "max_seq_len": 256,
  "dropout": 0.0,
  "bias": false,
  "rope_theta": 10000.0,
  "downsample_factors": [
    1,
    2,
    4
  ],
  "num_parameters": 14376192,
  "training_results": {
    "model": "AXL-Translate",
    "params": 15174400,
    "steps": 3942,
    "time": 600.0003161430359,
    "final_loss": 0.6703445315361023,
    "perplexity": 1.86,
    "max_seq_len": 256
  }
}