{
  "_name_or_path": "/home/user/Documents/nanotron/models/Llama3-8B-1.58-100B-tokens",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": 128009,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "is_bitnet_config": true,
  "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,
  "quantization_config": {
    "modules_to_not_convert": [
      "self_attn.q_proj",
      "self_attn.k_proj", 
      "self_attn.v_proj",
      "self_attn.o_proj",
      "mlp.gate_proj",
      "mlp.up_proj",
      "mlp.down_proj"
    ],
    "quant_method": "bitnet"
  },
  "rms_norm_eps": 1e-05,
  "rope_interleaved": false,
  "rope_scaling": null,
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.46.3",
  "use_cache": true,
  "vocab_size": 128256
}