{
  "_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
  "architectures": [
    "MistralForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 32768,
  "model_type": "mistral",
  "neuron": {
    "auto_cast_type": "bf16",
    "batch_size": 4,
    "checkpoint_id": "HuggingFaceH4/zephyr-7b-beta",
    "checkpoint_revision": "dc24cabd13eacd3ae3a5fe574bd645483a335a4a",
    "compiler_type": "neuronx-cc",
    "compiler_version": "2.12.54.0+f631c2365",
    "num_cores": 2,
    "sequence_length": 2048,
    "task": "text-generation"
  },
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pad_token_id": 2,
  "rms_norm_eps": 1e-05,
  "rope_theta": 10000.0,
  "sliding_window": 4096,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.36.2",
  "use_cache": true,
  "vocab_size": 32000
}