HeshamHaroon commited on
Commit
b613c61
1 Parent(s): 00fb4c8

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +6 -6
app.py CHANGED
@@ -38,7 +38,7 @@ tokenizer_options = [
38
  "inception-mbzuai/jais-13b",
39
  "aubmindlab/bert-base-arabertv2",
40
  "CohereForAI/c4ai-command-r-v01",
41
- "CohereForAI/c4ai-command-r-plus"
42
  ]
43
 
44
  if meta_llama_tokenizer:
@@ -73,13 +73,13 @@ def compare_tokenizers(tokenizer_name, text):
73
  tokens_display = [token.encode('utf-8').decode('utf-8') if isinstance(token, bytes) else token for token in tokens]
74
 
75
  # Prepare the results to be displayed in HTML format
76
- tokens_html = "".join([f"<span style='background-color:#D3D3D3; padding:2px; margin:2px; border-radius:5px;'>{token}</span>" for token in tokens_display])
77
- encoded_html = "".join([f"<span style='background-color:#ADD8E6; padding:2px; margin:2px; border-radius:5px;'>{token}</span>" for token in encoded_output])
78
- decoded_html = f"<div style='background-color:#90EE90; padding:10px; border-radius:5px;'>{decoded_text}</div>"
79
 
80
  results_html = f"""
81
  <div style='font-family: Arial, sans-serif;'>
82
- <h3>Tokenizer: {tokenizer_name}</h3>
83
  <p><strong>Tokens:</strong> {tokens_html}</p>
84
  <p><strong>Encoded:</strong> {encoded_html}</p>
85
  <p><strong>Decoded:</strong> {decoded_html}</p>
@@ -89,7 +89,7 @@ def compare_tokenizers(tokenizer_name, text):
89
 
90
  # Define the Gradio interface components with a dropdown for model selection
91
  inputs_component = [
92
- gr.Dropdown(choices=tokenizer_options, label="Select Tokenizer"),
93
  gr.Textbox(lines=2, placeholder="اكتب النص هنا...", label="Input Text")
94
  ]
95
 
 
38
  "inception-mbzuai/jais-13b",
39
  "aubmindlab/bert-base-arabertv2",
40
  "CohereForAI/c4ai-command-r-v01",
41
+ "CohereForAI/c4ai-command-r-plus"
42
  ]
43
 
44
  if meta_llama_tokenizer:
 
73
  tokens_display = [token.encode('utf-8').decode('utf-8') if isinstance(token, bytes) else token for token in tokens]
74
 
75
  # Prepare the results to be displayed in HTML format
76
+ tokens_html = "".join([f"<span style='background-color:#f0f0f0; padding:4px; margin:2px; border-radius:3px; border:1px solid #ccc;'>{token}</span>" for token in tokens_display])
77
+ encoded_html = "".join([f"<span style='background-color:#e0f7fa; padding:4px; margin:2px; border-radius:3px; border:1px solid #00acc1;'>{token}</span>" for token in encoded_output])
78
+ decoded_html = f"<div style='background-color:#e8f5e9; padding:10px; border-radius:3px; border:1px solid #4caf50;'>{decoded_text}</div>"
79
 
80
  results_html = f"""
81
  <div style='font-family: Arial, sans-serif;'>
82
+ <h3 style='color: #00796b;'>Tokenizer: {tokenizer_name}</h3>
83
  <p><strong>Tokens:</strong> {tokens_html}</p>
84
  <p><strong>Encoded:</strong> {encoded_html}</p>
85
  <p><strong>Decoded:</strong> {decoded_html}</p>
 
89
 
90
  # Define the Gradio interface components with a dropdown for model selection
91
  inputs_component = [
92
+ gr.Dropdown(choices=tokenizer_options, label="Select Tokenizer", type="index"),
93
  gr.Textbox(lines=2, placeholder="اكتب النص هنا...", label="Input Text")
94
  ]
95