config.json

{
  "_name_or_path": "google/gemma-2-27b-it",
  "architectures": [
    "Gemma2ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attn_logit_softcapping": 50.0,
  "bos_token_id": 2,
  "cache_implementation": "hybrid",
  "eos_token_id": 1,
  "final_logit_softcapping": 30.0,
  "head_dim": 128,
  "hidden_act": "gelu_pytorch_tanh",
  "hidden_activation": "gelu_pytorch_tanh",
  "hidden_size": 4608,
  "initializer_range": 0.02,
  "intermediate_size": 36864,
  "max_position_embeddings": 8192,
  "model_type": "gemma2",
  "num_attention_heads": 32,
  "num_hidden_layers": 46,
  "num_key_value_heads": 16,
  "pad_token_id": 0,
  "quantization_config": {
    "_load_in_4bit": true,
    "_load_in_8bit": false,
    "bnb_4bit_compute_dtype": "bfloat16",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "fp4",
    "bnb_4bit_use_double_quant": true,
    "llm_int8_enable_fp32_cpu_offload": true,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": [
      "model.layers.37",
      "model.layers.38",
      "model.layers.39",
      "model.layers.40",
      "model.layers.41",
      "model.layers.42",
      "model.layers.43",
      "model.layers.44",
      "model.layers.45",
      "lm_head"
    ],
    "llm_int8_threshold": 6.0,
    "load_in_4bit": true,
    "load_in_8bit": false,
    "quant_method": "bitsandbytes"
  },
  "query_pre_attn_scalar": 144,
  "rms_norm_eps": 1e-06,
  "rope_theta": 10000.0,
  "sliding_window": 4096,
  "sliding_window_size": 4096,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.43.0.dev0",
  "use_cache": true,
  "vocab_size": 256000
}