Transformers, what can they do?

[jzaba123]

Hello,

Going via the training.
Some small ideas for improvements.

#######################

Transformers, what can they do?
https://huggingface.co/learn/nlp-course/en/chapter1/3

A)
Current code sample
is incomplete

from transformers import pipeline

classifier = pipeline("sentiment-analysis")
classifier("I've been waiting for a HuggingFace course my whole life.")

CORRECT COULD BE
B)
from transformers import pipeline

classifier = pipeline("sentiment-analysis")
result = classifier("I've been waiting for a HuggingFace course my whole life.")
print(result)

C)
Even better could be

import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3' # Suppresses TensorFlow logs
os.environ['TF_ENABLE_ONEDNN_OPTS'] = '0' # Disables oneDNN custom operations

from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification
import warnings
import torch

import tensorflow as tf
tf.get_logger().setLevel('ERROR')

Set environment variable to disable oneDNN custom operations warning (specific to TensorFlow)

os.environ['TF_ENABLE_ONEDNN_OPTS'] = '0'

Suppress warnings

warnings.filterwarnings('ignore', category=DeprecationWarning)

Check if a GPU is available

device = 0 if torch.cuda.is_available() else -1

Load the tokenizer with the clean_up_tokenization_spaces parameter set

tokenizer = AutoTokenizer.from_pretrained(
"distilbert/distilbert-base-uncased-finetuned-sst-2-english",
clean_up_tokenization_spaces=True
)

Load the model in PyTorch

model = AutoModelForSequenceClassification.from_pretrained(
"distilbert/distilbert-base-uncased-finetuned-sst-2-english"
)

Initialize the sentiment-analysis pipeline with the custom tokenizer and PyTorch model

classifier = pipeline(
"sentiment-analysis",
model=model,
framework='pt', # Use PyTorch
tokenizer=tokenizer,
device=device # Use GPU if available, otherwise use CPU
)

result = classifier(
["I've been waiting for a HuggingFace course my whole life.", "I hate this so much!"]
)

print(result)

######################

https://huggingface.co/learn/nlp-course/en/chapter8/5
transformers-cli env

• transformers version: 4.44.0
• Platform: Windows-10-10.0.22631-SP0
• Python version: 3.11.9
• Huggingface_hub version: 0.24.5
• Safetensors version: 0.4.4
• Accelerate version: 0.33.0
• Accelerate config: not found
• PyTorch version (GPU?): 2.4.0+cu118 (True)
• Tensorflow version (GPU?): 2.17.0 (False)
• Flax version (CPU?/GPU?/TPU?): 0.7.0 (cpu)
• Jax version: 0.4.13
• JaxLib version: 0.4.13
• Using distributed or parallel set-up in the script?:
• Using GPU in script?:
• GPU type: NVIDIA GeForce RTX 3060 Laptop GPU

[osanseviero]

I moved the issue to the corresponding repo