{
  "_name_or_path": "/kaggle/KoboldAI_all/models/EXAONE-3.5-7.8B-Instruct",
  "activation_function": "silu",
  "architectures": [
    "ExaoneForCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_exaone.ExaoneConfig",
    "AutoModelForCausalLM": "modeling_exaone.ExaoneForCausalLM",
    "AutoModelForSequenceClassification": "modeling_exaone.ExaoneForSequenceClassification"
  },
  "bos_token_id": 1,
  "embed_dropout": 0.0,
  "eos_token_id": 361,
  "head_dim": 128,
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "layer_norm_epsilon": 1e-05,
  "max_position_embeddings": 32768,
  "model_type": "exaone",
  "num_attention_heads": 32,
  "num_key_value_heads": 8,
  "num_layers": 32,
  "pad_token_id": 0,
  "quantization_config": {
    "_load_in_4bit": false,
    "_load_in_8bit": true,
    "bnb_4bit_compute_dtype": "float32",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "fp4",
    "bnb_4bit_use_double_quant": false,
    "llm_int8_enable_fp32_cpu_offload": true,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": null,
    "llm_int8_threshold": 6.0,
    "load_in_4bit": false,
    "load_in_8bit": true,
    "quant_method": "bitsandbytes"
  },
  "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": 1000000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.47.0",
  "use_cache": false,
  "vocab_size": 102400
}