config.json

{
  "model_type": "smb_unstructured",
  "architectures": [
    "SMBUnstructuredForCausalLM"
  ],
  "llm_model_name_or_path": "./Meta-Llama-3-8B",
  "tokenizer_name_or_path": "./Meta-Llama-3-8B",
  "hidden_size": 4096,
  "vocab_size": 128272,
  "pad_token": "<|end_of_text|>",
  "pad_token_id": 128001,
  "tokenizer_padding_side": "right",
  "tokenizer_model_max_length": 3300,
  "use_cache": true,
  "auto_map": {
    "AutoConfig": "modeling_smb_unstructured.SMBUnstructuredConfig",
    "AutoModelForCausalLM": "modeling_smb_unstructured.SMBUnstructuredForCausalLM"
  },
  "text_config": {
    "_name_or_path": "./Meta-Llama-3-8B",
    "architectures": [
      "LlamaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 128000,
    "eos_token_id": 128001,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 14336,
    "max_position_embeddings": 8192,
    "mlp_bias": false,
    "model_type": "llama",
    "num_attention_heads": 32,
    "num_hidden_layers": 32,
    "num_key_value_heads": 8,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 500000.0,
    "torch_dtype": "bfloat16",
    "use_cache": true,
    "vocab_size": 128272
  }
}