Instructions to use asritha22bce/bart-positive-tone with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use asritha22bce/bart-positive-tone with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("asritha22bce/bart-positive-tone") model = AutoModelForSeq2SeqLM.from_pretrained("asritha22bce/bart-positive-tone", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download handler.py from asritha22bce/bart-positive-tone: direct link, hf CLI and curl.
- Browser
- Download file 931 Bytes
-
https://huggingface.co/asritha22bce/bart-positive-tone/resolve/main/handler.py
- Command line
-
hf download hf://asritha22bce/bart-positive-tone/handler.py
-
curl -L -o handler.py https://huggingface.co/asritha22bce/bart-positive-tone/resolve/main/handler.py
931 Bytes
| from transformers import AutoModelForSeq2SeqLM, AutoTokenizer | |
| import torch | |
| class ModelHandler: | |
| def __init__(self): | |
| self.model_path = "asritha22bce/bart-positive-tone" # Change if needed | |
| self.model = AutoModelForSeq2SeqLM.from_pretrained(self.model_path) | |
| self.tokenizer = AutoTokenizer.from_pretrained(self.model_path) | |
| def preprocess(self, text): | |
| return self.tokenizer(text, return_tensors="pt", truncation=True, padding=True) | |
| def inference(self, inputs): | |
| with torch.no_grad(): | |
| output_ids = self.model.generate(**inputs, max_length=50) | |
| return self.tokenizer.decode(output_ids[0], skip_special_tokens=True) | |
| def postprocess(self, output): | |
| return {"positive_headline": output} | |
| handler = ModelHandler() | |
| def handle_request(text): | |
| inputs = handler.preprocess(text) | |
| output = handler.inference(inputs) | |
| return handler.postprocess(output) | |