# Error when running run\_summarization.py

**URL:** <https://discuss.huggingface.co/t/error-when-running-run-summarization-py/51991>\
**Category:** Beginners\
**Created:** [August 24, 2023, 3:23pm UTC](https://discuss.huggingface.co/t/error-when-running-run-summarization-py/51991 "2023-08-24T15:23:11Z")\
**Posts on this page:** 6\
**Page:** 1

<div class="post-metadata">

**Author:** ![darkhorse82](https://avatars.discourse-cdn.com/v4/letter/d/e0b2c6/32.png) [@darkhorse82](https://discuss.huggingface.co/u/darkhorse82)\
**Post date:** [August 24, 2023, 3:23pm UTC](https://discuss.huggingface.co/t/error-when-running-run-summarization-py/51991/1 "2023-08-24T15:23:11Z")

</div>

Hi,

I am trying to run this simple run\_summarization.py following this page:

> <https://github.com/huggingface/optimum-intel/tree/main/examples/neural_compressor/summarization>
>
> //github.com/huggingface/optimum-intel/tree/main/examples/neural\_compressor/summarization

Below are the error messages that I obtained:

(base) smgailab@upfspr:~/Intel/optimum-intel/examples/neural\_compressor/summarization$ python run\_summarization.py   
–model\_name\_or\_path t5-small  
–dataset\_name=cnn\_dailymail   
–dataset\_config “3.0.0”  
–source\_prefix "summarize: "   
–apply\_quantization   
–apply\_pruning   
–target\_sparsity 0.1   
–num\_train\_epochs 4   
–max\_train\_samples 100   
–do\_train   
–do\_eval   
–verify\_loading   
–predict\_with\_generate   
–per\_device\_train\_batch\_size=4   
–per\_device\_eval\_batch\_size=4   
–output\_dir /tmp/test\_summarization

run\_summarization.py: error: the following arguments are required: --model\_name\_or\_path, --output\_dir  
–model\_name\_or\_path: command not found  
–dataset\_name=cnn\_dailymail: command not found  
–source\_prefix: command not found

System info:  
Distributor ID: Ubuntu  
Description: Ubuntu 22.04 LTS  
Release: 22.04  
Python 3.11.4  
Model name: Intel(R) Xeon(R) Platinum 8480+

---

<div class="post-metadata">

**Author:** ![muellerzr](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/muellerzr/32/21583_2.png) [@muellerzr](https://discuss.huggingface.co/u/muellerzr)\
**Post date:** [August 24, 2023, 3:48pm UTC](https://discuss.huggingface.co/t/error-when-running-run-summarization-py/51991/2 "2023-08-24T15:48:52Z")

</div>

> [@darkhorse82](#):
>
> –

Command arguments need two dashes (`--`) not one like you are using (`-`)

Also in the future, please try and use back-ticks for code blocks and commands, it makes things easier for the rest of us! (the (`) char)

---

<div class="post-metadata">

**Author:** ![darkhorse82](https://avatars.discourse-cdn.com/v4/letter/d/e0b2c6/32.png) [@darkhorse82](https://discuss.huggingface.co/u/darkhorse82)\
**Post date:** [August 24, 2023, 3:54pm UTC](https://discuss.huggingface.co/t/error-when-running-run-summarization-py/51991/3 "2023-08-24T15:54:50Z")

</div>

Hi there,

I am using double dashes… i think something went wrong when i copy and paste from the terminal.

python run\_summarization.py \   
–model\_name\_or\_path t5-small  
–dataset\_name=cnn\_dailymail   
–dataset\_config “3.0.0”  
–source\_prefix "summarize: "   
–apply\_quantization   
–apply\_pruning   
–target\_sparsity 0.1   
–num\_train\_epochs 4   
–max\_train\_samples 100   
–do\_train   
–do\_eval   
–verify\_loading   
–predict\_with\_generate   
–per\_device\_train\_batch\_size=4   
–per\_device\_eval\_batch\_size=4   
–output\_dir /tmp/test\_summarization

 ![image](https://us1.discourse-cdn.com/hellohellohello/original/3X/0/5/05b9d9edbd374e1402a422c75c2f6299ddffb793.png)

---

<div class="post-metadata">

**Author:** ![darkhorse82](https://avatars.discourse-cdn.com/v4/letter/d/e0b2c6/32.png) [@darkhorse82](https://discuss.huggingface.co/u/darkhorse82)\
**Post date:** [August 24, 2023, 3:55pm UTC](https://discuss.huggingface.co/t/error-when-running-run-summarization-py/51991/4 "2023-08-24T15:55:25Z")

</div>

![image](https://us1.discourse-cdn.com/hellohellohello/original/3X/d/4/d46ec2447cb889d023cac91c2522701e0ae7ddb5.png)

---

<div class="post-metadata">

**Author:** ![darkhorse82](https://avatars.discourse-cdn.com/v4/letter/d/e0b2c6/32.png) [@darkhorse82](https://discuss.huggingface.co/u/darkhorse82)\
**Post date:** [August 24, 2023, 4:16pm UTC](https://discuss.huggingface.co/t/error-when-running-run-summarization-py/51991/5 "2023-08-24T16:16:53Z")

</div>

eventually i think something wrong with torch.quantization?

(base) smgailab@upfspr:~/Intel/optimum-intel/examples/neural\_compressor/summarization$ ./run\_summarization.sh  
Traceback (most recent call last):  
File “/home/smgailab/Intel/optimum-intel/examples/neural\_compressor/summarization/run\_summarization.py”, line 53, in   
from optimum.intel.neural\_compressor import INCModelForSeq2SeqLM, INCSeq2SeqTrainer  
File “/home/smgailab/miniconda3/lib/python3.11/site-packages/optimum/intel/neural\_compressor/ **init**.py”, line 16, in   
from .quantization import (  
File “/home/smgailab/miniconda3/lib/python3.11/site-packages/optimum/intel/neural\_compressor/quantization.py”, line 29, in   
from torch.quantization import add\_observer\_, convert  
ImportError: cannot import name ‘add\_observer\_’ from ‘torch.quantization’ (/home/smgailab/miniconda3/lib/python3.11/site-packages/torch/quantization/ **init**.py)  
./run\_summarization.sh: line 2: --model\_name\_or\_path: command not found  
./run\_summarization.sh: line 5: --source\_prefix: command not found

This is my run\_summarization.sh file

![image](https://us1.discourse-cdn.com/hellohellohello/original/3X/e/1/e1203526859cc3478dc673d71ecdc4e31084b79c.png)

---

<div class="post-metadata">

**Author:** ![muellerzr](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/muellerzr/32/21583_2.png) [@muellerzr](https://discuss.huggingface.co/u/muellerzr)\
**Post date:** [August 24, 2023, 4:44pm UTC](https://discuss.huggingface.co/t/error-when-running-run-summarization-py/51991/6 "2023-08-24T16:44:21Z")

</div>

> [@darkhorse82](#):
>
> ImportError: cannot import name ‘add\_observer\_’ from ‘torch.quantization’ (/home/smgailab/miniconda3/lib/python3.11/site-packages/torch/quantization/ **init**.py)

You may want to update your torch version then perhaps.