config.json

{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_probs_dropout_prob": 0.0,
  "bos_token_id": 50256,
  "custom_pipelines": {
    "text-generation": {
      "impl": "h2oai_pipeline.H2OTextGenerationPipeline",
      "pt": "AutoModelForCausalLM"
    }
  },
  "eos_token_id": 50256,
  "hidden_act": "silu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 8192,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "pad_token_id": 0,
  "rms_norm_eps": 1e-06,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.30.1",
  "use_cache": true,
  "vocab_size": 51200
}