bakhitovd commited on
Commit
ac3ab1f
1 Parent(s): 59c8196

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -9,14 +9,14 @@ pipeline_tag: summarization
9
  # Fine-tuned Longformer for Summarization of Machine Learning Articles
10
 
11
  ## Model Details
12
- - GitHub: https://github.com/Bakhitovd/MS_in_Data_Science_Capstone
13
  - Model name: bakhitovd/led-base-7168-ml
14
  - Model type: Longformer (alenai/led-base-16384)
15
  - Model description: This Longformer model has been fine-tuned on a focused subset of the arXiv part of the scientific papers dataset, specifically targeting articles about Machine Learning. It aims to generate accurate and consistent summaries of machine learning research papers.
16
  ## Intended Use
17
  This model is intended to be used for text summarization tasks, specifically for summarizing machine learning research papers.
18
  ## How to Use
19
- ```
20
  import torch
21
  from transformers import LEDTokenizer, LEDForConditionalGeneration
22
  tokenizer = LEDTokenizer.from_pretrained("bakhitovd/led-base-7168-ml")
@@ -24,7 +24,7 @@ model = LEDForConditionalGeneration.from_pretrained("bakhitovd/led-base-7168-ml"
24
  ```
25
 
26
  ## Use the model for summarization
27
- ```
28
  article = "... long document ..."
29
  inputs_dict = tokenizer.encode(article, padding="max_length", max_length=16384, return_tensors="pt", truncation=True)
30
  input_ids = inputs_dict.input_ids.to("cuda")
 
9
  # Fine-tuned Longformer for Summarization of Machine Learning Articles
10
 
11
  ## Model Details
12
+ - GitHub: https://github.com/Bakhitovd/led-base-7168-ml
13
  - Model name: bakhitovd/led-base-7168-ml
14
  - Model type: Longformer (alenai/led-base-16384)
15
  - Model description: This Longformer model has been fine-tuned on a focused subset of the arXiv part of the scientific papers dataset, specifically targeting articles about Machine Learning. It aims to generate accurate and consistent summaries of machine learning research papers.
16
  ## Intended Use
17
  This model is intended to be used for text summarization tasks, specifically for summarizing machine learning research papers.
18
  ## How to Use
19
+ ```python
20
  import torch
21
  from transformers import LEDTokenizer, LEDForConditionalGeneration
22
  tokenizer = LEDTokenizer.from_pretrained("bakhitovd/led-base-7168-ml")
 
24
  ```
25
 
26
  ## Use the model for summarization
27
+ ```python
28
  article = "... long document ..."
29
  inputs_dict = tokenizer.encode(article, padding="max_length", max_length=16384, return_tensors="pt", truncation=True)
30
  input_ids = inputs_dict.input_ids.to("cuda")