{
  "_name_or_path": "/egr/research-optml/jiajingh/.cache/hub/models--ibm-granite--granite-3.3-8b-instruct/snapshots/51dd4bc2ade4059a6bd87649d68aa11e4fb2529b",
  "architectures": [
    "GraniteForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attention_multiplier": 0.0078125,
  "bos_token_id": 0,
  "embedding_multiplier": 12.0,
  "eos_token_id": 0,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 12800,
  "logits_scaling": 16.0,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "granite",
  "num_attention_heads": 32,
  "num_hidden_layers": 40,
  "num_key_value_heads": 8,
  "pad_token_id": 0,
  "residual_multiplier": 0.22,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000000.0,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.49.0",
  "use_cache": true,
  "vocab_size": 49159
}