{
  "_attn_implementation_autoset": true,
  "_name_or_path": "NousResearch/Yarn-Llama-2-7b-128k",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "NousResearch/Yarn-Llama-2-7b-128k--configuration_llama.LlamaConfig",
    "AutoModelForCausalLM": "NousResearch/Yarn-Llama-2-7b-128k--modeling_llama_together_yarn.LlamaForCausalLM"
  },
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 131072,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "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": false,
    "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"
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 32.0,
    "finetuned": true,
    "original_max_position_embeddings": 4096,
    "type": "yarn"
  },
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.46.0",
  "use_cache": false,
  "use_flash_attention": false,
  "vocab_size": 32000
}