Helsinki-NLP

/

opus-mt-mul-en

like 69

Follow

Language Technology Research Group at the University of Helsinki 298

With this input,

"תאגיד הדלק והכימיקלים של סין (באנגלית: China Petroleum & Chemical Corporation, בסינית: 中国石油化工股份有限公司) או סינופק (אנגלית: Sinopec Limited, סינית: 中国石化, סינית מסורתית: 中國石化, פין-יין: Zhōngguó Shíhuà) היא תאגיד נפט וגז ממשלתי סיני הממוקם בבייג'ינג."

the model throws the error for transformers==4.31.0:

---------------------------------------------------------------------------
IndexError                                Traceback (most recent call last)
<ipython-input-31-e2292311132f> in <module>
----> 1 translator(s)

~/Library/Python/3.8/lib/python/site-packages/transformers/pipelines/text2text_generation.py in __call__(self, *args, **kwargs)
    365               token ids of the translation.
    366         """
--> 367         return super().__call__(*args, **kwargs)

~/Library/Python/3.8/lib/python/site-packages/transformers/pipelines/text2text_generation.py in __call__(self, *args, **kwargs)
    163         """
    164 
--> 165         result = super().__call__(*args, **kwargs)
    166         if (
    167             isinstance(args[0], list)

~/Library/Python/3.8/lib/python/site-packages/transformers/pipelines/base.py in __call__(self, inputs, num_workers, batch_size, *args, **kwargs)
   1120             )
   1121         else:
-> 1122             return self.run_single(inputs, preprocess_params, forward_params, postprocess_params)
   1123 
   1124     def run_multi(self, inputs, preprocess_params, forward_params, postprocess_params):

~/Library/Python/3.8/lib/python/site-packages/transformers/pipelines/base.py in run_single(self, inputs, preprocess_params, forward_params, postprocess_params)
   1127     def run_single(self, inputs, preprocess_params, forward_params, postprocess_params):
   1128         model_inputs = self.preprocess(inputs, **preprocess_params)
-> 1129         model_outputs = self.forward(model_inputs, **forward_params)
   1130         outputs = self.postprocess(model_outputs, **postprocess_params)
   1131         return outputs

~/Library/Python/3.8/lib/python/site-packages/transformers/pipelines/base.py in forward(self, model_inputs, **forward_params)
   1026                 with inference_context():
   1027                     model_inputs = self._ensure_tensor_on_device(model_inputs, device=self.device)
-> 1028                     model_outputs = self._forward(model_inputs, **forward_params)
   1029                     model_outputs = self._ensure_tensor_on_device(model_outputs, device=torch.device("cpu"))
   1030             else:

~/Library/Python/3.8/lib/python/site-packages/transformers/pipelines/text2text_generation.py in _forward(self, model_inputs, **generate_kwargs)
    185         generate_kwargs["max_length"] = generate_kwargs.get("max_length", self.model.config.max_length)
    186         self.check_inputs(input_length, generate_kwargs["min_length"], generate_kwargs["max_length"])
--> 187         output_ids = self.model.generate(**model_inputs, **generate_kwargs)
    188         out_b = output_ids.shape[0]
    189         if self.framework == "pt":

~/Library/Python/3.8/lib/python/site-packages/torch/utils/_contextlib.py in decorate_context(*args, **kwargs)

~/Library/Python/3.8/lib/python/site-packages/transformers/generation/utils.py in generate(self, inputs, generation_config, logits_processor, stopping_criteria, prefix_allowed_tokens_fn, synced_gpus, assistant_model, streamer, **kwargs)
   1625             )
   1626             # 13. run beam search
-> 1627             return self.beam_search(
   1628                 input_ids,
   1629                 beam_scorer,

~/Library/Python/3.8/lib/python/site-packages/transformers/generation/utils.py in beam_search(self, input_ids, beam_scorer, logits_processor, stopping_criteria, max_length, pad_token_id, eos_token_id, output_attentions, output_hidden_states, output_scores, return_dict_in_generate, synced_gpus, **model_kwargs)
   2930             model_inputs = self.prepare_inputs_for_generation(input_ids, **model_kwargs)
   2931 
-> 2932             outputs = self(
   2933                 **model_inputs,
   2934                 return_dict=True,

~/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py in _call_impl(self, *args, **kwargs)
   1499     def parameters(self, recurse: bool = True) -> Iterator[Parameter]:
   1500         r"""Returns an iterator over module parameters.
-> 1501 
   1502         This is typically passed to an optimizer.
   1503 

~/Library/Python/3.8/lib/python/site-packages/transformers/models/marian/modeling_marian.py in forward(self, input_ids, attention_mask, decoder_input_ids, decoder_attention_mask, head_mask, decoder_head_mask, cross_attn_head_mask, encoder_outputs, past_key_values, inputs_embeds, decoder_inputs_embeds, labels, use_cache, output_attentions, output_hidden_states, return_dict)
   1454                 )
   1455 
-> 1456         outputs = self.model(
   1457             input_ids,
   1458             attention_mask=attention_mask,

~/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py in _call_impl(self, *args, **kwargs)
   1499     def parameters(self, recurse: bool = True) -> Iterator[Parameter]:
   1500         r"""Returns an iterator over module parameters.
-> 1501 
   1502         This is typically passed to an optimizer.
   1503 

~/Library/Python/3.8/lib/python/site-packages/transformers/models/marian/modeling_marian.py in forward(self, input_ids, attention_mask, decoder_input_ids, decoder_attention_mask, head_mask, decoder_head_mask, cross_attn_head_mask, encoder_outputs, past_key_values, inputs_embeds, decoder_inputs_embeds, use_cache, output_attentions, output_hidden_states, return_dict)
   1256 
   1257         # decoder outputs consists of (dec_features, past_key_value, dec_hidden, dec_attn)
-> 1258         decoder_outputs = self.decoder(
   1259             input_ids=decoder_input_ids,
   1260             attention_mask=decoder_attention_mask,

~/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py in _call_impl(self, *args, **kwargs)
   1499     def parameters(self, recurse: bool = True) -> Iterator[Parameter]:
   1500         r"""Returns an iterator over module parameters.
-> 1501 
   1502         This is typically passed to an optimizer.
   1503 

~/Library/Python/3.8/lib/python/site-packages/transformers/models/marian/modeling_marian.py in forward(self, input_ids, attention_mask, encoder_hidden_states, encoder_attention_mask, head_mask, cross_attn_head_mask, past_key_values, inputs_embeds, use_cache, output_attentions, output_hidden_states, return_dict)
    999 
   1000         # embed positions
-> 1001         positions = self.embed_positions(input_shape, past_key_values_length)
   1002 
   1003         hidden_states = inputs_embeds + positions

~/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py in _call_impl(self, *args, **kwargs)
   1499     def parameters(self, recurse: bool = True) -> Iterator[Parameter]:
   1500         r"""Returns an iterator over module parameters.
-> 1501 
   1502         This is typically passed to an optimizer.
   1503 

~/Library/Python/3.8/lib/python/site-packages/torch/utils/_contextlib.py in decorate_context(*args, **kwargs)

~/Library/Python/3.8/lib/python/site-packages/transformers/models/marian/modeling_marian.py in forward(self, input_ids_shape, past_key_values_length)
    138             past_key_values_length, past_key_values_length + seq_len, dtype=torch.long, device=self.weight.device
    139         )
--> 140         return super().forward(positions)
    141 
    142 

~/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/sparse.py in forward(self, input)
    160             self.norm_type, self.scale_grad_by_freq, self.sparse)
    161 
--> 162     def extra_repr(self) -> str:
    163         s = '{num_embeddings}, {embedding_dim}'
    164         if self.padding_idx is not None:

~/Library/Python/3.8/lib/python/site-packages/torch/nn/functional.py in embedding(input, weight, padding_idx, max_norm, norm_type, scale_grad_by_freq, sparse)
   2208     else:
   2209         raise ValueError("mode has to be one of sum, mean or max")
-> 2210 
   2211     if max_norm is not None:
   2212         # XXX: equivalent to

IndexError: index out of range in self

To replicate the error:

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
from transformers import pipeline


tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-mul-en")
model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-mul-en")


translator = pipeline("translation", tokenizer=tokenizer, model=model, max_length=1024)

s = "תאגיד הדלק והכימיקלים של סין (באנגלית: China Petroleum & Chemical Corporation, בסינית: 中国石油化工股份有限公司) או סינופק (אנגלית: Sinopec Limited, סינית: 中国石化, סינית מסורתית: 中國石化, פין-יין: Zhōngguó Shíhuà) היא תאגיד נפט וגז ממשלתי סיני הממוקם בבייג'ינג."

translator(s, src_lang="he")