Why would the tokenizer for encoder-decoder model for machine translation use bos_token_id == eos_token_id? How does it know when a sequence ends?

I see on this PyTorch model Helsinki-NLP/opus-mt-fr-en (HuggingFace), which is an encoder-decoder model for machine translation:

  "bos_token_id": 0,
  "eos_token_id": 0,

in its config.json.

Why set bos_token_id == eos_token_id? How does it know when a sequence ends?

By comparison, I see that facebook/mbart-large-50 uses in its config.json a different ID:

  "bos_token_id": 0,
  "eos_token_id": 2,

Entire config.json for Helsinki-NLP/opus-mt-fr-en:

{
  "_name_or_path": "/tmp/Helsinki-NLP/opus-mt-fr-en",
  "_num_labels": 3,
  "activation_dropout": 0.0,
  "activation_function": "swish",
  "add_bias_logits": false,
  "add_final_layer_norm": false,
  "architectures": [
    "MarianMTModel"
  ],
  "attention_dropout": 0.0,
  "bad_words_ids": [
    [
      59513
    ]
  ],
  "bos_token_id": 0,
  "classif_dropout": 0.0,
  "classifier_dropout": 0.0,
  "d_model": 512,
  "decoder_attention_heads": 8,
  "decoder_ffn_dim": 2048,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 6,
  "decoder_start_token_id": 59513,
  "decoder_vocab_size": 59514,
  "dropout": 0.1,
  "encoder_attention_heads": 8,
  "encoder_ffn_dim": 2048,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 6,
  "eos_token_id": 0,
  "forced_eos_token_id": 0,
  "gradient_checkpointing": false,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2"
  },
  "init_std": 0.02,
  "is_encoder_decoder": true,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_2": 2
  },
  "max_length": 512,
  "max_position_embeddings": 512,
  "model_type": "marian",
  "normalize_before": false,
  "normalize_embedding": false,
  "num_beams": 4,
  "num_hidden_layers": 6,
  "pad_token_id": 59513,
  "scale_embedding": true,
  "share_encoder_decoder_embeddings": true,
  "static_position_embeddings": true,
  "transformers_version": "4.22.0.dev0",
  "use_cache": true,
  "vocab_size": 59514
}

Entire config.json for facebook/mbart-large-50 :

{
  "_name_or_path": "/home/suraj/projects/mbart-50/hf_models/mbart-50-large",
  "_num_labels": 3,
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "add_bias_logits": false,
  "add_final_layer_norm": true,
  "architectures": [
    "MBartForConditionalGeneration"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 0,
  "classif_dropout": 0.0,
  "classifier_dropout": 0.0,
  "d_model": 1024,
  "decoder_attention_heads": 16,
  "decoder_ffn_dim": 4096,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 12,
  "decoder_start_token_id": 2,
  "dropout": 0.1,
  "early_stopping": true,
  "encoder_attention_heads": 16,
  "encoder_ffn_dim": 4096,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 12,
  "eos_token_id": 2,
  "forced_eos_token_id": 2,
  "gradient_checkpointing": false,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2"
  },
  "init_std": 0.02,
  "is_encoder_decoder": true,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_2": 2
  },
  "max_length": 200,
  "max_position_embeddings": 1024,
  "model_type": "mbart",
  "normalize_before": true,
  "normalize_embedding": true,
  "num_beams": 5,
  "num_hidden_layers": 12,
  "output_past": true,
  "pad_token_id": 1,
  "scale_embedding": true,
  "static_position_embeddings": false,
  "transformers_version": "4.4.0.dev0",
  "use_cache": true,
  "vocab_size": 250054,
  "tokenizer_class": "MBart50Tokenizer"
}

Crossposts:

• https://ai.stackexchange.com/q/48427/4
• https://qr.ae/pAAezR
• https://redd.it/1k3vdl7
• https://redd.it/1k3vddf
• https://redd.it/1k3vdri
• https://redd.it/1k3vdu5
• https://redd.it/1k3vdwy
• https://redd.it/1k3vdxy
• https://redd.it/1k3ve37
• https://redd.it/1k3ve6z
• https://redd.it/1k3vedz

posted about 10 hours ago

CC BY-SA 4.0

10h ago

Franck Dernoncourt‭

91 reputation 16 6 13 27