Open sankexin opened 2 weeks ago
Hello, I used your code here without the above bugs. Please try to update the transformers library.
Hello, I used your code here without the above bugs. Please try to update the transformers library.
I have tested many transformers, which transformers do you used?can you share your detail env?
hello, my transformers version is 4.44.2
hello, my transformers version is 4.44.2
done
Is there an existing issue ? / 是否已有相关的 issue ?
Describe the bug / 描述这个 bug
File /opt/conda/lib/python3.10/site-packages/transformers/tokenization_utils_fast.py:576, in PreTrainedTokenizerFast._encode_plus(self, text, text_pair, add_special_tokens, padding_strategy, truncation_strategy, max_length, stride, is_split_into_words, pad_to_multiple_of, return_tensors, return_token_type_ids, return_attention_mask, return_overflowing_tokens, return_special_tokens_mask, return_offsets_mapping, return_length, verbose, kwargs) 554 def _encode_plus( 555 self, 556 text: Union[TextInput, PreTokenizedInput], (...) 573 kwargs, 574 ) -> BatchEncoding: 575 batched_input = [(text, text_pair)] if text_pair else [text] --> 576 batched_output = self._batch_encode_plus( 577 batched_input, 578 is_split_into_words=is_split_into_words, 579 add_special_tokens=add_special_tokens, 580 padding_strategy=padding_strategy, 581 truncation_strategy=truncation_strategy, 582 max_length=max_length, 583 stride=stride, 584 pad_to_multiple_of=pad_to_multiple_of, 585 return_tensors=return_tensors, 586 return_token_type_ids=return_token_type_ids, 587 return_attention_mask=return_attention_mask, 588 return_overflowing_tokens=return_overflowing_tokens, 589 return_special_tokens_mask=return_special_tokens_mask, 590 return_offsets_mapping=return_offsets_mapping, 591 return_length=return_length, 592 verbose=verbose, 593 **kwargs, 594 ) 596 # Return tensor is None, then we can remove the leading batch axis 597 # Overflowing tokens are returned as a batch of output so we keep them in this case 598 if return_tensors is None and not return_overflowing_tokens:
TypeError: PreTrainedTokenizerFast._batch_encode_plus() got an unexpected keyword argument 'tools'
To Reproduce / 如何复现
from transformers import AutoModelForCausalLM, AutoTokenizer import torch
path = "openbmb/MiniCPM3-4B" device = "cuda"
tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained(path, torch_dtype=torch.bfloat16, device_map=device, trust_remote_code=True)
messages = [ {"role": "user", "content": "推荐5个北京的景点。"}, ] model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(device)
model_outputs = model.generate( model_inputs, max_new_tokens=1024, top_p=0.7, temperature=0.7 )
output_token_ids = [ model_outputs[i][len(model_inputs[i]):] for i in range(len(model_inputs)) ]
responses = tokenizer.batch_decode(output_token_ids, skip_special_tokens=True)[0] print(responses)
Expected behavior / 期望的结果
No response
Screenshots / 截图
No response
Environment / 环境
Additional context / 其他信息
No response