config.json

{
  "_name_or_path": "/fast/gsu/downloadmodels/models--meta-llama--Meta-Llama-3-8B/snapshots/8cde5ca8380496c9a6cc7ef3a8b46a0372a1d920",
  "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": "customllama",
  "auto_map": {
    "AutoConfig": "configuration_customllama.CustomLlamaConfig",
    "AutoModelForCausalLM": "modeling_customllama.CustomLlamaForCausalLM"
  },
  "num_attention_heads": 32,
  "num_hidden_layers": 23,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 500000.0,
  "scales": [
    1.0,
    1.079885812438952,
    1.0,
    1.0,
    1.0,
    1.0,
    1.0,
    1.0,
    1.0,
    1.0,
    1.0,
    1.0,
    0.9519616816038667,
    1.0,
    1.0,
    1.0,
    1.0403642462118812,
    1.0,
    1.0,
    1.0,
    1.0861791836554266,
    1.1246551701322038,
    1.0
  ],
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.45.2",
  "use_cache": true,
  "vocab_size": 128256
}