config.json

{
  "activation_type": "silu",
  "alibi": false,
  "alibi_bias_max": 8.0,
  "architectures": [
    "LLaDAModelLM"
  ],
  "attention_dropout": 0.0,
  "attention_layer_norm": false,
  "attention_layer_norm_with_affine": true,
  "auto_map": {
    "AutoConfig": "configuration_llada_engram.LLaDAConfig",
    "AutoModelForCausalLM": "modeling_llada_engram.LLaDAModelLM",
    "AutoModel": "modeling_llada_engram.LLaDAModelLM"
  },
  "bias_for_layer_norm": false,
  "block_group_size": 1,
  "block_type": "llama",
  "d_model": 768,
  "embedding_dropout": 0.0,
  "embedding_size": 7424,
  "eos_token_id": 6624,
  "flash_attention": false,
  "include_bias": false,
  "include_qkv_bias": false,
  "init_cutoff_factor": null,
  "init_device": "meta",
  "init_fn": "mitchell",
  "init_std": 0.02,
  "input_emb_norm": false,
  "layer_norm_type": "rms",
  "layer_norm_with_affine": true,
  "mask_token_id": 7186,
  "max_sequence_length": 128,
  "mlp_hidden_size": 1536,
  "model_type": "llada",
  "multi_query_attention": null,
  "n_heads": 12,
  "n_kv_heads": 12,
  "n_layers": 14,
  "pad_token_id": 6624,
  "precision": "amp_bf16",
  "residual_dropout": 0.0,
  "rms_norm_eps": 1e-05,
  "rope": true,
  "rope_full_precision": true,
  "rope_theta": 500000.0,
  "scale_logits": false,
  "transformers_version": "4.46.3",
  "use_cache": false,
  "vocab_size": 7397,
  "weight_tying": false,
  "engram_config": {
    "tokenizer_name_or_path": "./tokenizer.json",
    "engram_vocab_size": [
      51200,
      51200,
      51200
    ],
    "max_ngram_size": 4,
    "n_embed_per_ngram": 256,
    "n_head_per_ngram": 4,
    "layer_ids": [
      1,
      7
    ],
    "pad_id": 6629,
    "seed": 42,
    "kernel_size": 7
  }
}