{
  "architectures": [
    "Cola2ForConditionalGeneration"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_cola2.Cola2Config",
    "AutoModel": "modeling_cola2.Cola2ForConditionalGeneration",
    "AutoModelForCausalLM": "modeling_cola2.Cola2ForConditionalGeneration"
  },
  "bos_token_id": 151643,
  "boundary_score_alpha": 10.0,
  "boundary_score_threshold": 0.5,
  "cola2_format_version": 1,
  "condition_num_attention_heads": 20,
  "condition_rope_theta": 500000.0,
  "decoder_condition_num_hidden_layers": 2,
  "decoder_head_dim": 128,
  "decoder_hidden_size": 2560,
  "decoder_intermediate_size": 9728,
  "decoder_lm_head_bias": true,
  "decoder_num_attention_heads": 32,
  "decoder_num_hidden_layers": 36,
  "decoder_num_key_value_heads": 8,
  "decoder_rope_theta": 1000000.0,
  "diffusion_time": 1000.0,
  "dit_block_size": 8,
  "dit_head_dim": 128,
  "dit_hidden_size": 2560,
  "dit_intermediate_size": 10240,
  "dit_layer_norm_eps": 1e-05,
  "dit_num_attention_heads": 20,
  "dit_num_hidden_layers": 34,
  "dit_rope_dim": 96,
  "dit_rope_theta": 10000.0,
  "duration_hidden_size": 1280,
  "encoder_embedding_size": 2560,
  "encoder_hidden_size": 1536,
  "encoder_intermediate_size": 6144,
  "encoder_num_attention_heads": 12,
  "encoder_num_hidden_layers": 0,
  "encoder_rope_theta": 500000.0,
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_dropout": 0.0,
  "im_end_token_id": 151645,
  "im_start_token_id": 151644,
  "initializer_range": 0.02,
  "latent_block_causal": false,
  "latent_block_size": 8,
  "latent_decoder_num_hidden_layers": 0,
  "latent_dim": 64,
  "latent_encoder_num_hidden_layers": 2,
  "layer_norm_eps": 1e-06,
  "local_position_dim": 128,
  "mask_token_id": 151936,
  "max_position_embeddings": 32768,
  "max_span_length": 8,
  "min_span_length": 1,
  "model_type": "cola2",
  "pad_token_id": 151936,
  "pool_num_hidden_layers": 2,
  "preset": "cola2",
  "rope_theta": 1000000.0,
  "scaling_factor": 1.0,
  "shifting_factor": 0.0,
  "target_compression_rate": 0.5,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "use_variational_encoder": true,
  "vocab_size": 151936
}