Update README.md
Browse files
README.md
CHANGED
|
@@ -99,30 +99,31 @@ code::after {
|
|
| 99 |
</div>
|
| 100 |
|
| 101 |
|
| 102 |
-
<
|
| 103 |
-
<code>
|
|
|
|
| 104 |
from transformers import BartTokenizer, BartForConditionalGeneration
|
| 105 |
from datasets import load_dataset
|
| 106 |
|
| 107 |
-
Load pre-trained BART model for summarization
|
| 108 |
tokenizer = BartTokenizer.from_pretrained('ayjays132/EnhancerModel')
|
| 109 |
model = BartForConditionalGeneration.from_pretrained('ayjays132/EnhancerModel')
|
| 110 |
|
| 111 |
-
Load dataset
|
| 112 |
dataset = load_dataset("cnn_dailymail", "3.0.0")
|
| 113 |
|
| 114 |
-
Function to generate summary
|
| 115 |
def summarize(text):
|
| 116 |
inputs = tokenizer(text, return_tensors="pt", max_length=1024, truncation=True)
|
| 117 |
summary_ids = model.generate(inputs['input_ids'], max_length=150, min_length=40, length_penalty=2.0, num_beams=4, early_stopping=True)
|
| 118 |
return tokenizer.decode(summary_ids[0], skip_special_tokens=True)
|
| 119 |
|
| 120 |
-
|
| 121 |
print("Type of dataset['test']:", type(dataset['test']))
|
| 122 |
print("Type of the first element in dataset['test']:", type(dataset['test'][0]))
|
| 123 |
print("Content of the first element in dataset['test']:", dataset['test'][0])
|
| 124 |
|
| 125 |
-
Test the model on a few examples
|
| 126 |
for example in dataset['test'][:5]:
|
| 127 |
try:
|
| 128 |
# If the example is a string, then it's likely that 'dataset['test']' is not loaded as expected
|
|
@@ -139,5 +140,6 @@ for example in dataset['test'][:5]:
|
|
| 139 |
print("No 'article' field found in this example.")
|
| 140 |
except Exception as e:
|
| 141 |
print(f"Error processing example: {e}")
|
| 142 |
-
|
| 143 |
-
</div>
|
|
|
|
|
|
| 99 |
</div>
|
| 100 |
|
| 101 |
|
| 102 |
+
<body>
|
| 103 |
+
<div class="code-container">
|
| 104 |
+
<pre><code>
|
| 105 |
from transformers import BartTokenizer, BartForConditionalGeneration
|
| 106 |
from datasets import load_dataset
|
| 107 |
|
| 108 |
+
# Load pre-trained BART model for summarization
|
| 109 |
tokenizer = BartTokenizer.from_pretrained('ayjays132/EnhancerModel')
|
| 110 |
model = BartForConditionalGeneration.from_pretrained('ayjays132/EnhancerModel')
|
| 111 |
|
| 112 |
+
# Load dataset
|
| 113 |
dataset = load_dataset("cnn_dailymail", "3.0.0")
|
| 114 |
|
| 115 |
+
# Function to generate summary
|
| 116 |
def summarize(text):
|
| 117 |
inputs = tokenizer(text, return_tensors="pt", max_length=1024, truncation=True)
|
| 118 |
summary_ids = model.generate(inputs['input_ids'], max_length=150, min_length=40, length_penalty=2.0, num_beams=4, early_stopping=True)
|
| 119 |
return tokenizer.decode(summary_ids[0], skip_special_tokens=True)
|
| 120 |
|
| 121 |
+
# Debugging: Print the type and content of the first example
|
| 122 |
print("Type of dataset['test']:", type(dataset['test']))
|
| 123 |
print("Type of the first element in dataset['test']:", type(dataset['test'][0]))
|
| 124 |
print("Content of the first element in dataset['test']:", dataset['test'][0])
|
| 125 |
|
| 126 |
+
# Test the model on a few examples
|
| 127 |
for example in dataset['test'][:5]:
|
| 128 |
try:
|
| 129 |
# If the example is a string, then it's likely that 'dataset['test']' is not loaded as expected
|
|
|
|
| 140 |
print("No 'article' field found in this example.")
|
| 141 |
except Exception as e:
|
| 142 |
print(f"Error processing example: {e}")
|
| 143 |
+
</code></pre>
|
| 144 |
+
</div>
|
| 145 |
+
</body>
|