# BlenderBot forward method crashing **URL:** \ **Category:** Models\ **Created:** [May 26, 2022, 8:14pm UTC](https://discuss.huggingface.co/t/blenderbot-forward-method-crashing/18410 "2022-05-26T20:14:28Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![0xrushi](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/0xrushi/32/43372_2.png) [@0xrushi](https://discuss.huggingface.co/u/0xrushi)\ **Post date:** [May 26, 2022, 8:14pm UTC](https://discuss.huggingface.co/t/blenderbot-forward-method-crashing/18410/1 "2022-05-26T20:14:29Z")
I am trying to use [BlenderbotForConditionalGeneration](https://huggingface.co/docs/transformers/v4.19.2/en/model_doc/blenderbot#transformers.BlenderbotForConditionalGeneration), and I’m getting the following error ```auto --------------------------------------------------------------------------- IndexError Traceback (most recent call last) in () 2 input_ids = encoding['input_ids'], 3 attention_mask = encoding['attention_mask'], ----> 4 labels=labels) 9 frames /usr/local/lib/python3.7/dist-packages/torch/nn/functional.py in embedding(input, weight, padding_idx, max_norm, norm_type, scale_grad_by_freq, sparse) 2181 # remove once script supports set_grad_enabled 2182 _no_grad_embedding_renorm_(weight, input, max_norm, norm_type) -> 2183 return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse) 2184 2185 IndexError: index out of range in self ``` **Actual Code** ```auto MODEL_NAME = "facebook/blenderbot-400M-distill" tokenizer = BlenderbotTokenizer.from_pretrained(MODEL_NAME) encoding = tokenizer( sample_question['question'], sample_question['context'], max_length=1024, padding='max_length', truncation="only_second", return_attention_mask=True, add_special_tokens=True, return_tensors="pt" ) answer_encoding = tokenizer( sample_question['answer_text'], max_length=1024, padding='max_length', truncation=True, return_attention_mask=True, add_special_tokens=True, return_tensors="pt" ) labels = answer_encoding["input_ids"] model = BlenderbotForConditionalGeneration.from_pretrained(MODEL_NAME, return_dict = True) output = model( input_ids = encoding['input_ids'], attention_mask = encoding['attention_mask'], labels = labels ) ``` ---
**Author:** ![thies](https://avatars.discourse-cdn.com/v4/letter/t/ed655f/32.png) [@thies](https://discuss.huggingface.co/u/thies)\ **Post date:** [May 27, 2022, 12:50pm UTC](https://discuss.huggingface.co/t/blenderbot-forward-method-crashing/18410/2 "2022-05-27T12:50:16Z")
As it crashes during the embedding lookup, did you check that the vocabulary file is the correct one? ---
**Author:** ![0xrushi](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/0xrushi/32/43372_2.png) [@0xrushi](https://discuss.huggingface.co/u/0xrushi)\ **Post date:** [May 27, 2022, 2:27pm UTC](https://discuss.huggingface.co/t/blenderbot-forward-method-crashing/18410/3 "2022-05-27T14:27:51Z")
Hi @thies!, Thanks for checking. I got it resolved over the discord, The issue was in the tokenizer max\_length was wrong. The best way to find this would be checking `model.config.max_position_embeddings`. ```auto tokenizer( data_row['question'], data_row['context'], max_length=128 ) ``` ---
**Author:** ![0xrushi](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/0xrushi/32/43372_2.png) [@0xrushi](https://discuss.huggingface.co/u/0xrushi)\ **Post date:** [May 27, 2022, 2:41pm UTC](https://discuss.huggingface.co/t/blenderbot-forward-method-crashing/18410/4 "2022-05-27T14:41:02Z")
If anyone is interested in the notebook link: [here](https://github.com/rushic24/deep-learning-notebooks/blob/main/temp-notebooks/BlenderBotQuestionAnswering.ipynb). I hardcoded max\_len to 128, by looking at the model.config.