com3dian commited on
Commit
236082d
1 Parent(s): cd7a246

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -6
README.md CHANGED
@@ -19,7 +19,7 @@ pipeline_tag: summarization
19
 
20
  ![Bart Logo](https://huggingface.co/front/assets/huggingface_logo.svg)
21
 
22
- This repository contains the **Bart-Large-paper2slides-summarizer Model**, which has been fine-tuned on the [Automatic Slide Generation from Scientific Papers dataset](https://www.kaggle.com/datasets/andrewmvd/automatic-slide-generation-from-scientific-papers) using unsupervised learning techniques using an algorithm from the paper entitled 'unsupervised machine translation'.
23
  Its primary focus is to summarize **scientific texts** with precision and accuracy, the model is parallelly trained with another model from the same contributor,
24
 
25
  ## Model Details
@@ -40,18 +40,23 @@ To use this model, you can leverage the Hugging Face [Transformers](https://hugg
40
  from transformers import BartTokenizer, BartForConditionalGeneration
41
 
42
  # Load the model and tokenizer
43
- model_name = "your-username/bart-large-slide-generation"
44
  tokenizer = BartTokenizer.from_pretrained(model_name)
45
  model = BartForConditionalGeneration.from_pretrained(model_name)
46
 
47
- # Generate slides from input text
48
  input_text = "Your input text here..."
49
  input_ids = tokenizer.encode(input_text, return_tensors="pt")
50
  output = model.generate(input_ids)
51
 
52
- # Decode generated slides
53
- slides = tokenizer.decode(output[0], skip_special_tokens=True)
54
- print(slides)
 
 
 
 
 
55
  ```
56
 
57
  Ensure you have the `transformers` library installed before running the code. You can install it using `pip`:
 
19
 
20
  ![Bart Logo](https://huggingface.co/front/assets/huggingface_logo.svg)
21
 
22
+ This repository contains the **Bart-Large-paper2slides-summarizer Model**, which has been fine-tuned on the [Automatic Slide Generation from Scientific Papers dataset](https://www.kaggle.com/datasets/andrewmvd/automatic-slide-generation-from-scientific-papers) using unsupervised learning techniques using an algorithm from the paper entitled '[Unsupervised Machine Translation Using Monolingual Corpora Only](https://arxiv.org/abs/1711.00043)'.
23
  Its primary focus is to summarize **scientific texts** with precision and accuracy, the model is parallelly trained with another model from the same contributor,
24
 
25
  ## Model Details
 
40
  from transformers import BartTokenizer, BartForConditionalGeneration
41
 
42
  # Load the model and tokenizer
43
+ model_name = "com3dian/Bart-large-paper2slides-summarizer"
44
  tokenizer = BartTokenizer.from_pretrained(model_name)
45
  model = BartForConditionalGeneration.from_pretrained(model_name)
46
 
47
+ # Generate summary from input text
48
  input_text = "Your input text here..."
49
  input_ids = tokenizer.encode(input_text, return_tensors="pt")
50
  output = model.generate(input_ids)
51
 
52
+ # Decode generated summaries
53
+ summary = tokenizer.decode(output[0], skip_special_tokens=True)
54
+ print(summary)
55
+
56
+ # Or using the pipeline API
57
+ summarizer = pipeline("summarization", model=model_name)
58
+ summary = summarizer(text, max_length=50, min_length=30, do_sample=False)
59
+ print(summary)
60
  ```
61
 
62
  Ensure you have the `transformers` library installed before running the code. You can install it using `pip`: