{
  "_name_or_path": "/home/anmol/nips_challenge/efficiency_challenge_repo/code/00_starter_repo/neurips_llm_efficiency_challenge/sample-submissions/llama_recipes/models_saved/32_8_mistral_model_exodus_4d0d33a1-e716-41fb-99c1-b6ad3fb75080/WHOLE_best_model_yet_epoch_1_3",
  "architectures": [
    "MistralForCausalLM"
  ],
  "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",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "rms_norm_eps": 1e-05,
  "rope_theta": 10000.0,
  "sliding_window": 4096,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.34.1",
  "use_cache": true,
  "vocab_size": 32000
}