Instructions to use Lin0He/text-summary-gpt2-short with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Lin0He/text-summary-gpt2-short with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "summarization" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("summarization", model="Lin0He/text-summary-gpt2-short")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Lin0He/text-summary-gpt2-short") model = AutoModelForCausalLM.from_pretrained("Lin0He/text-summary-gpt2-short", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update pipeline.py
Browse files- pipeline.py +2 -2
pipeline.py
CHANGED
|
@@ -65,9 +65,9 @@ class PreTrainedPipeline():
|
|
| 65 |
self.tokenizer = AutoTokenizer.from_pretrained("Lin0He/text-summary-gpt2-short")
|
| 66 |
self.model = AutoModelForCausalLM.from_pretrained("Lin0He/text-summary-gpt2-short")
|
| 67 |
|
| 68 |
-
def __call__(self, data) ->
|
| 69 |
# process input
|
| 70 |
inputs = data#.pop("inputs", data)
|
| 71 |
# process input text
|
| 72 |
prediction = model_infer(self.model, self.tokenizer, inputs+"TL;DR")
|
| 73 |
-
return
|
|
|
|
| 65 |
self.tokenizer = AutoTokenizer.from_pretrained("Lin0He/text-summary-gpt2-short")
|
| 66 |
self.model = AutoModelForCausalLM.from_pretrained("Lin0He/text-summary-gpt2-short")
|
| 67 |
|
| 68 |
+
def __call__(self, data) -> str:
|
| 69 |
# process input
|
| 70 |
inputs = data#.pop("inputs", data)
|
| 71 |
# process input text
|
| 72 |
prediction = model_infer(self.model, self.tokenizer, inputs+"TL;DR")
|
| 73 |
+
return prediction
|