{
  "_name_or_path": "xglm-564M",
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "architectures": [
    "XGLMForCausalLM"
  ],
  "attention_dropout": 0.1,
  "attention_heads": 16,
  "bos_token_id": 0,
  "classifier_dropout": 0.0,
  "d_model": 1024,
  "decoder_attention_heads": 16,
  "decoder_ffn_dim": 4096,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 24,
  "decoder_start_token_id": 2,
  "dropout": 0.1,
  "encoder_layerdrop": 0.0,
  "eos_token_id": 2,
  "ffn_dim": 4096,
  "init_std": 0.02,
  "layerdrop": 0.0,
  "max_position_embeddings": 2048,
  "model_type": "xglm",
  "num_layers": 24,
  "pad_token_id": 1,
  "scale_embedding": true,
  "torch_dtype": "float16",
  "transformers_version": "4.15.0.dev0",
  "use_cache": true,
  "vocab_size": 256008
}