# Token restriction via the Huggin face API

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftoken-restriction-via-the-huggin-face-api%2F112370%3E%5C
**Category:** Beginners\
**Created:** [October 16, 2024, 12:33pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftoken-restriction-via-the-huggin-face-api%2F112370 "2024-10-16T12:33:15Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [October 16, 2024, 1:05pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftoken-restriction-via-the-huggin-face-api%2F112370%2F2 "2024-10-16T13:05:47Z")

</div>

I’m also DeepL. No problem.  
Normally this is the way to increase max\_new\_tokens, but without a way to specify it on the botpress side, there is no way to do it.

> [@How do I increase max\_new\_tokens](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-do-i-increase-max-new-tokens%2F43098%2F4)%3A
>
> @gkrishnan I’m late to the post but you can always manually pass in the model/pipeline: from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer from langchain.llms import HuggingFacePipeline model = AutoModelForCausalLM.from\_pretrained(model\_path) tokenizer = AutoTokenizer.from\_pretrained(model\_path) gen = pipeline('text-generation', model=model, tokenizer=tokenizer, max\_new\_tokens=200) llama\_llm = HuggingFacePipeline(pipeline=gen)

> [@Confused about max\_length and max\_new\_tokens](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fconfused-about-max-length-and-max-new-tokens%2F30892%2F6)%3A
>
> I know I’m late now. But for any future preferences. what the max\_length and max\_new\_tokens do. In max\_length we get the maximum length including the input and output tokens. But in max\_new\_tokens we get the maximum output excluding the output. Let me show you using the code import torch from transformers import AutoModelForCausalLM, AutoTokenizer,AutoModelForSeq2SeqLM torch.set\_default\_device("cuda") model = AutoModelForCausalLM.from\_pretrained("microsoft/phi-2", torch\_dtype="auto", tru…

The botpress people seem to be on HF, so there’s always the option of sending them a direct mentions and asking them. (@+username)

> **[Botpress (Botpress)](https://huggingface.co/Botpress)**
>
> NLP, Conversational AI

---

_[View the full topic](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftoken-restriction-via-the-huggin-face-api%2F112370)._