config.json

{
  "architectures": [
    "MaskedDiffusionModel"
  ],
  "model_type": "llada",
  "vocab_size": 50257,
  "hidden_size": 1024,
  "num_hidden_layers": 12,
  "num_attention_heads": 16,
  "intermediate_size": 4096,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "attention_probs_dropout_prob": 0.1,
  "max_position_embeddings": 512,
  "initializer_range": 0.02,
  "layer_norm_eps": 1e-12,
  "pad_token_id": 50256,
  "bos_token_id": 50256,
  "eos_token_id": 50256,
  "num_timesteps": 100,
  "masking_schedule": "uniform"
}