# Implementing bad\_words\_ids does not work with OPT models!

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fimplementing-bad-words-ids-does-not-work-with-opt-models%2F20839%3E%5C
**Category:** Beginners\
**Created:** [July 25, 2022, 1:43pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fimplementing-bad-words-ids-does-not-work-with-opt-models%2F20839 "2022-07-25T13:43:18Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![anujn](https://avatars.discourse-cdn.com/v4/letter/a/5f9b8f/32.png) [@anujn](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fanujn)%5C
**Post date:** [July 25, 2022, 1:43pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fimplementing-bad-words-ids-does-not-work-with-opt-models%2F20839%2F1 "2022-07-25T13:43:18Z")

</div>

Hey HF,

I have been trying to impliment bad\_words\_ids argument into model.generate but it doesnt seem to work with the OPT models:

```auto
from transformers import pipeline, set_seed

set_seed(32)

prompt = "I go to the post office"

tokenizer = AutoTokenizer.from_pretrained("facebook/opt-1.3b", use_fast=False, add_prefix_space=True, add_special_tokens=False)

input_ids = tokenizer(prompt, return_tensors="pt").input_ids.cuda()

badwords = ["envelope"]
bad_words_ids = tokenizer(badwords).input_ids

generated_ids = model.generate(input_ids, do_sample=True, max_length=150, bad_words_ids=bad_words_ids, eos_token_id = 2)

tokenizer.batch_decode(generated_ids, skip_special_tokens=True)

```

Am I doing something wrong or does this not work of the OPT models?