{
  "architectures": [
    "FP8LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_fp8_llama.FP8LlamaConfig",
    "AutoModel": "modeling_fp8_llama.FP8LlamaModel",
    "AutoModelForCausalLM": "modeling_fp8_llama.FP8LlamaForCausalLM",
    "AutoModelForQuestionAnswering": "modeling_fp8_llama.FP8LlamaForQuestionAnswering",
    "AutoModelForSequenceClassification": "modeling_fp8_llama.FP8LlamaForSequenceClassification",
    "AutoModelForTokenClassification": "modeling_fp8_llama.FP8LlamaForTokenClassification"
  },
  "bos_token_id": 128000,
  "dtype": "bfloat16",
  "eos_token_id": [
    128001,
    128008,
    128009
  ],
  "fp8_config": {
    "act_block_size": 16,
    "float8_dtype": "torch.float8_e4m3fn",
    "layer_name": "",
    "mm_block_size": 128,
    "quant_type": "DIV",
    "training_mode": true
  },
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_name_orig": "meta-llama/Llama-3.1-8B-Instruct",
  "model_type": "fp8_llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 8.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "transformers_version": "4.57.0",
  "use_cache": true,
  "vocab_size": 128256
}