Welcome to Software Development on Codidact!

Will you help us build our independent community of developers helping developers? We're small and trying to grow. We welcome questions about all aspects of software development, from design to code to QA and more. Got questions? Got answers? Got code you'd like someone to review? Please join us.

Post History

50%

+0 −0

Q&A 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. ...

0 answers · posted 14h ago by Franck Dernoncourt‭ · edited 14h ago by Franck Dernoncourt‭

#4: Post edited by

Franck Dernoncourt‭ · 2025-04-20T20:20:42Z (about 14 hours ago)

Copy Link

Raw

Markdown

I see on this PyTorch model [`Helsinki-NLP/opus-mt-fr-en`](https://huggingface.co/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`](https://huggingface.co/Helsinki-NLP/opus-mt-fr-en/blob/main/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`](https://huggingface.co/facebook/mbart-large-50/blob/main/config.json) a different ID:
```
"bos_token_id": 0,
"eos_token_id": 2,
```
----
Entire [`config.json`](https://huggingface.co/Helsinki-NLP/opus-mt-fr-en/blob/main/config.json) for [`Helsinki-NLP/opus-mt-fr-en`](https://huggingface.co/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`](https://huggingface.co/facebook/mbart-large-50/blob/main/config.json) for [`facebook/mbart-large-50
`](https://huggingface.co/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~~

I see on this PyTorch model [`Helsinki-NLP/opus-mt-fr-en`](https://huggingface.co/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`](https://huggingface.co/Helsinki-NLP/opus-mt-fr-en/blob/main/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`](https://huggingface.co/facebook/mbart-large-50/blob/main/config.json) a different ID:
```
"bos_token_id": 0,
"eos_token_id": 2,
```
----
Entire [`config.json`](https://huggingface.co/Helsinki-NLP/opus-mt-fr-en/blob/main/config.json) for [`Helsinki-NLP/opus-mt-fr-en`](https://huggingface.co/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`](https://huggingface.co/facebook/mbart-large-50/blob/main/config.json) for [`facebook/mbart-large-50
`](https://huggingface.co/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

#3: Post edited by

Franck Dernoncourt‭ · 2025-04-20T20:07:30Z (about 14 hours ago)

Copy Link

Raw

Markdown

~~Why would the tokenizer for encoder-decoder model for machine translation use bos_token_id == eos_token_id?~~

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`](https://huggingface.co/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`](https://huggingface.co/Helsinki-NLP/opus-mt-fr-en/blob/main/config.json).
~~Why set bos_token_id == eos_token_id?~~
By comparison, I see that facebook/mbart-large-50 uses in its [`config.json`](https://huggingface.co/facebook/mbart-large-50/blob/main/config.json) a different ID:
```
"bos_token_id": 0,
"eos_token_id": 2,
```
----
Entire [`config.json`](https://huggingface.co/Helsinki-NLP/opus-mt-fr-en/blob/main/config.json) for [`Helsinki-NLP/opus-mt-fr-en`](https://huggingface.co/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`](https://huggingface.co/facebook/mbart-large-50/blob/main/config.json) for [`facebook/mbart-large-50
`](https://huggingface.co/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

I see on this PyTorch model [`Helsinki-NLP/opus-mt-fr-en`](https://huggingface.co/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`](https://huggingface.co/Helsinki-NLP/opus-mt-fr-en/blob/main/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`](https://huggingface.co/facebook/mbart-large-50/blob/main/config.json) a different ID:
```
"bos_token_id": 0,
"eos_token_id": 2,
```
----
Entire [`config.json`](https://huggingface.co/Helsinki-NLP/opus-mt-fr-en/blob/main/config.json) for [`Helsinki-NLP/opus-mt-fr-en`](https://huggingface.co/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`](https://huggingface.co/facebook/mbart-large-50/blob/main/config.json) for [`facebook/mbart-large-50
`](https://huggingface.co/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

#2: Post edited by

Franck Dernoncourt‭ · 2025-04-20T20:04:22Z (about 14 hours ago)

Copy Link

Raw

Markdown

I see on this PyTorch model [`Helsinki-NLP/opus-mt-fr-en`](https://huggingface.co/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`](https://huggingface.co/Helsinki-NLP/opus-mt-fr-en/blob/main/config.json).
Why set bos_token_id == eos_token_id?
By comparison, I see that facebook/mbart-large-50 uses in its [`config.json`](https://huggingface.co/facebook/mbart-large-50/blob/main/config.json) a different ID:
```
"bos_token_id": 0,
"eos_token_id": 2,
```
----
Entire [`config.json`](https://huggingface.co/Helsinki-NLP/opus-mt-fr-en/blob/main/config.json) for [`Helsinki-NLP/opus-mt-fr-en`](https://huggingface.co/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`](https://huggingface.co/facebook/mbart-large-50/blob/main/config.json) for [`facebook/mbart-large-50
`](https://huggingface.co/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"
}
~~```~~

I see on this PyTorch model [`Helsinki-NLP/opus-mt-fr-en`](https://huggingface.co/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`](https://huggingface.co/Helsinki-NLP/opus-mt-fr-en/blob/main/config.json).
Why set bos_token_id == eos_token_id?
By comparison, I see that facebook/mbart-large-50 uses in its [`config.json`](https://huggingface.co/facebook/mbart-large-50/blob/main/config.json) a different ID:
```
"bos_token_id": 0,
"eos_token_id": 2,
```
----
Entire [`config.json`](https://huggingface.co/Helsinki-NLP/opus-mt-fr-en/blob/main/config.json) for [`Helsinki-NLP/opus-mt-fr-en`](https://huggingface.co/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`](https://huggingface.co/facebook/mbart-large-50/blob/main/config.json) for [`facebook/mbart-large-50
`](https://huggingface.co/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

#1: Initial revision by

Franck Dernoncourt‭ · 2025-04-20T20:03:03Z (about 14 hours ago)

Copy Link

Raw

Markdown

Why would the tokenizer for encoder-decoder model for machine translation use bos_token_id == eos_token_id?

I see on this PyTorch model [`Helsinki-NLP/opus-mt-fr-en`](https://huggingface.co/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`](https://huggingface.co/Helsinki-NLP/opus-mt-fr-en/blob/main/config.json).

Why set bos_token_id == eos_token_id?

By comparison, I see that facebook/mbart-large-50 uses in its [`config.json`](https://huggingface.co/facebook/mbart-large-50/blob/main/config.json) a different ID:


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


----

Entire [`config.json`](https://huggingface.co/Helsinki-NLP/opus-mt-fr-en/blob/main/config.json) for [`Helsinki-NLP/opus-mt-fr-en`](https://huggingface.co/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`](https://huggingface.co/facebook/mbart-large-50/blob/main/config.json) for [`facebook/mbart-large-50
`](https://huggingface.co/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"
}
```

pytorch machine-translation tokenization huggingface encoder-decoder

Communities

Post History