decoder_config.json

{
  "_attn_implementation_autoset": true,
  "_name_or_path": "/home/models/gemma2_9b-sg-inst",
  "architectures": [
    "Gemma2ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attn_logit_softcapping": 50.0,
  "cache_implementation": "hybrid",
  "eos_token_id": 107,
  "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,
  "query_pre_attn_scalar": 256,
  "rms_norm_eps": 1e-06,
  "rope_theta": 10000.0,
  "sliding_window": 4096,
  "sliding_window_size": 4096,
  "torch_dtype": "bfloat16",
  "use_cache": true,
  "vocab_size": 256000,
  "quantization": {
    "group_size": 64,
    "bits": 4,
    "mode": "affine"
  },
  "quantization_config": {
    "group_size": 64,
    "bits": 4,
    "mode": "affine"
  }
}