{
  "_name_or_path": "johntsi/nllb-200-distilled-600M_mustc_en-to-8",
  "activation_dropout": 0.0,
  "activation_function": "relu",
  "architectures": [
    "M2M100ForConditionalGeneration"
  ],
  "attention_dropout": 0.1,
  "bos_token_id": 0,
  "d_model": 1024,
  "decoder_attention_heads": 16,
  "decoder_ffn_dim": 4096,
  "decoder_layerdrop": 0,
  "decoder_layers": 12,
  "decoder_start_token_id": 2,
  "dropout": 0.1,
  "encoder_attention_heads": 16,
  "encoder_ffn_dim": 4096,
  "encoder_layerdrop": 0,
  "encoder_layers": 12,
  "eos_token_id": 2,
  "init_std": 0.02,
  "is_encoder_decoder": true,
  "max_length": 200,
  "max_position_embeddings": 1024,
  "model_type": "m2m_100",
  "num_hidden_layers": 12,
  "pad_token_id": 1,
  "scale_embedding": true,
  "tokenizer_class": "NllbTokenizer",
  "torch_dtype": "float32",
  "transformers_version": "4.41.2",
  "use_cache": true,
  "vocab_size": 256206
}