# How to add a stop sequence to a Pipeline?

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-add-a-stop-sequence-to-a-pipeline%2F99831%3E%5C
**Category:** 🤗Transformers\
**Created:** [July 29, 2024, 12:12am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-add-a-stop-sequence-to-a-pipeline%2F99831 "2024-07-29T00:12:56Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![jcalvo1234](https://avatars.discourse-cdn.com/v4/letter/j/9d8465/32.png) [@jcalvo1234](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fjcalvo1234)%5C
**Post date:** [July 29, 2024, 12:12am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-add-a-stop-sequence-to-a-pipeline%2F99831%2F1 "2024-07-29T00:12:56Z")

</div>

Hello,

I know I can do this with model.generate but I would like to know if it is possible to add an arg for an stop sequence with the Pipeline.

For example:

model = AutoModelForCausalLM.from\_pretrained(  
“microsoft/Phi-3-mini-128k-instruct”,  
device\_map=“cuda”,  
torch\_dtype=“auto”,  
trust\_remote\_code=True,  
)  
tokenizer = AutoTokenizer.from\_pretrained(“microsoft/Phi-3-mini-128k-instruct”)

pipe = pipeline(  
“text-generation”,  
model=model,  
tokenizer=tokenizer,  
max\_new\_tokens=1000,  
return\_full\_text=False,  
temperature=0.1,  
stop=[“my stop chars”]??? Here add my stop sequence argument which I am struggling to find how to do it  
)