private-llm-config.json

{
  "model_type": "gemma2",
  "quantization": "w4a16g128asym",
  "model_config": {
    "hidden_size": 2304,
    "hidden_act": "gelu_pytorch_tanh",
    "intermediate_size": 9216,
    "attention_bias": false,
    "num_attention_heads": 8,
    "num_key_value_heads": 4,
    "head_dim": 256,
    "num_hidden_layers": 26,
    "rms_norm_eps": 1e-06,
    "vocab_size": 256000,
    "position_embedding_base": 10000.0,
    "context_window_size": 4096,
    "prefill_chunk_size": 128,
    "tensor_parallel_shards": 1,
    "max_batch_size": 80,
    "attn_logit_softcapping": 50.0,
    "final_logit_softcapping": 30.0,
    "query_pre_attn_scalar": 256,
    "sliding_window": 4096
  },
  "vocab_size": 256000,
  "context_window_size": 4096,
  "sliding_window_size": -1,
  "prefill_chunk_size": 128,
  "attention_sink_size": -1,
  "tensor_parallel_shards": 1,
  "mean_gen_len": 128,
  "max_gen_len": 512,
  "shift_fill_factor": 0.3,
  "temperature": 0.7,
  "presence_penalty": 0.0,
  "frequency_penalty": 0.0,
  "repetition_penalty": 1.0,
  "top_p": 0.95,
  "conv_template": "gemma_instruction",
  "pad_token_id": 0,
  "bos_token_id": 2,
  "eos_token_id": [
    1,
    107
  ],
  "tokenizer_files": [
    "tokenizer.json",
    "tokenizer_config.json"
  ],
  "version": "0.1.0"
}