Chapter 1 questions

John6666 · May 28, 2025, 7:06am

I tend to use max_new_tokens.

"Both `max_new_tokens` and `max_length` have been set but they serve the same purpose" when only setting max_new_tokens.

opened 02:03PM - 30 Jan 23 UTC

closed 08:47PM - 30 Jan 23 UTC

### System Info - `transformers` version: 4.27.0.dev0 - Platform: Windows-10…-10.0.19044-SP0 - Python version: 3.10.4 - Huggingface_hub version: 0.12.0 - PyTorch version (GPU?): 1.13.1+cpu (False) - Tensorflow version (GPU?): not installed (NA) - Flax version (CPU?/GPU?/TPU?): not installed (NA) - Jax version: not installed - JaxLib version: not installed - Using GPU in script?: No - Using distributed or parallel set-up in script?: No ### Who can help? @gante I believe. ### Information - [ ] The official example scripts - [X] My own modified scripts ### Tasks - [X] An officially supported task in the `examples` folder (such as GLUE/SQuAD, ...) - [ ] My own task or dataset (give details below) ### Reproduction 1. Install transformers 2. Run the following script ``` from transformers import pipeline summarizer = pipeline("summarization", max_new_tokens=50) prompt = "text to summarize" summary = summarizer(prompt) ``` 3. It crashes with the following error: > ValueError: Both `max_new_tokens` and `max_length` have been set but they serve the same purpose -- setting a limit to the generated output length. Remove one of those arguments. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation) ### Expected behavior Expected behavior is that the script should run. I only set `max_new_tokens` and not `max_length`. This might seem like a duplicate of https://github.com/huggingface/transformers/issues/20894 but the issue persists even after installing the latest version of transformers with the fix for that issue.

Topic		Replies	Views
VisionEncoderDecoder/TrOCR Models	0	702	October 21, 2021
Chapter 3 questions Course	139	10088	May 3, 2025
T5 Model, T5 Encoder Model and T5 Model for Conditional Generation Beginners	1	1286	November 20, 2022
Using an encoder-decoder model for Recognizing Textual Entailment (GLUE task) Models	0	170	March 31, 2024
Which model of transformers to use if I want to do multiclassification of a pair of sentences containing a questionair 🤗Transformers	0	251	February 18, 2022

Chapter 1 questions

Related topics