config.json

{
  "_name_or_path": "google/gemma-2-9b",
  "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": 256,
  "hidden_act": "gelu_pytorch_tanh",
  "hidden_activation": "gelu_pytorch_tanh",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 8192,
  "model_type": "gemma2",
  "num_attention_heads": 16,
  "num_hidden_layers": 42,
  "num_key_value_heads": 8,
  "pad_token_id": 0,
  "quantization_config": {
    "batch_size": 1,
    "bits": 4,
    "block_name_to_quantize": null,
    "cache_block_outputs": true,
    "damp_percent": 0.1,
    "dataset": "c4",
    "desc_act": false,
    "exllama_config": {
      "version": 1
    },
    "group_size": 128,
    "max_input_length": null,
    "model_seqlen": null,
    "module_name_preceding_first_block": null,
    "modules_in_block_to_quantize": null,
    "pad_token_id": null,
    "quant_method": "gptq",
    "sym": true,
    "tokenizer": null,
    "true_sequential": true,
    "use_cuda_fp16": false,
    "use_exllama": true
  },
  "query_pre_attn_scalar": 256,
  "rms_norm_eps": 1e-06,
  "rope_theta": 10000.0,
  "sliding_window": 4096,
  "sliding_window_size": 4096,
  "torch_dtype": "float16",
  "transformers_version": "4.46.1",
  "use_cache": true,
  "vocab_size": 256000
}