yirmibesogluz commited on
Commit
3255b79
1 Parent(s): 7d6f3d4

Fixed image size and bullet lists

Browse files
Files changed (1) hide show
  1. app.py +20 -18
app.py CHANGED
@@ -14,17 +14,23 @@ Welcome to our Huggingface space, where you can explore the capabilities of TURN
14
  - **Powerful Architecture:** TURNA contains 1.1B parameters, and was pre-trained with an encoder-decoder architecture following the UL2 framework on 43B tokens from various domains.
15
  - **Diverse Training Data:** Our model is trained on a varied dataset of 43 billion tokens, covering a wide array of domains.
16
  - **Broad Applications:** TURNA is fine-tuned for a variety of generation and understanding tasks, including:
17
-
18
  - Summarization
19
- - Paraphrasing
20
- - News title generation
21
- - Sentiment classification
22
- - Text categorization
23
- - Named entity recognition
24
- - Part-of-speech tagging
25
- - Semantic textual similarity
26
- - Natural language inference
 
 
 
 
27
 
 
 
 
28
  Refer to our [paper](https://arxiv.org/abs/2401.14373) for more details.
29
 
30
  ### Citation
@@ -38,11 +44,6 @@ Refer to our [paper](https://arxiv.org/abs/2401.14373) for more details.
38
  primaryClass={cs.CL}
39
  }
40
  ```
41
-
42
- **Note:** First inference might take time as the models are downloaded on-the-go.
43
-
44
- *TURNA can generate toxic content or provide erroneous information. Double-check before usage.*
45
-
46
  """
47
 
48
 
@@ -138,12 +139,10 @@ def turna(input, max_new_tokens, length_penalty,
138
 
139
  with gr.Blocks(theme="abidlabs/Lime") as demo:
140
  gr.Markdown("# TURNA")
141
- gr.Image("images/turna-logo.png", width=100)
 
142
 
143
  gr.Markdown(DESCRIPTION)
144
-
145
-
146
-
147
 
148
  with gr.Tab("Sentiment Analysis"):
149
  gr.Markdown("TURNA fine-tuned on sentiment analysis. Enter text to analyse sentiment and pick the model (tweets or product reviews).")
@@ -265,4 +264,7 @@ with gr.Blocks(theme="abidlabs/Lime") as demo:
265
 
266
  sum_submit.click(summarize, inputs=[sum_input, sum_choice], outputs=sum_output)
267
  sum_examples = gr.Examples(examples = long_text, inputs = [sum_input, sum_choice], outputs=sum_output, fn=summarize)
 
 
 
268
  demo.launch()
 
14
  - **Powerful Architecture:** TURNA contains 1.1B parameters, and was pre-trained with an encoder-decoder architecture following the UL2 framework on 43B tokens from various domains.
15
  - **Diverse Training Data:** Our model is trained on a varied dataset of 43 billion tokens, covering a wide array of domains.
16
  - **Broad Applications:** TURNA is fine-tuned for a variety of generation and understanding tasks, including:
 
17
  - Summarization
18
+ - Paraphrasing
19
+ - News title generation
20
+ - Sentiment classification
21
+ - Text categorization
22
+ - Named entity recognition
23
+ - Part-of-speech tagging
24
+ - Semantic textual similarity
25
+ - Natural language inference
26
+
27
+ **Note:** First inference might take time as the models are downloaded on-the-go.
28
+
29
+ *TURNA can generate toxic content or provide erroneous information. Double-check before usage.*
30
 
31
+ """
32
+
33
+ CITATION = """
34
  Refer to our [paper](https://arxiv.org/abs/2401.14373) for more details.
35
 
36
  ### Citation
 
44
  primaryClass={cs.CL}
45
  }
46
  ```
 
 
 
 
 
47
  """
48
 
49
 
 
139
 
140
  with gr.Blocks(theme="abidlabs/Lime") as demo:
141
  gr.Markdown("# TURNA")
142
+ with gr.Row():
143
+ gr.Image("images/turna-logo.png", width=100)
144
 
145
  gr.Markdown(DESCRIPTION)
 
 
 
146
 
147
  with gr.Tab("Sentiment Analysis"):
148
  gr.Markdown("TURNA fine-tuned on sentiment analysis. Enter text to analyse sentiment and pick the model (tweets or product reviews).")
 
264
 
265
  sum_submit.click(summarize, inputs=[sum_input, sum_choice], outputs=sum_output)
266
  sum_examples = gr.Examples(examples = long_text, inputs = [sum_input, sum_choice], outputs=sum_output, fn=summarize)
267
+
268
+ gr.Markdown(CITATION)
269
+
270
  demo.launch()