shoaibanwar13
commited on
Upload my-model.py
Browse files- my-model.py +40 -0
my-model.py
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification, Trainer, TrainingArguments
|
2 |
+
from datasets import load_dataset
|
3 |
+
|
4 |
+
# Load a pre-trained tokenizer and model
|
5 |
+
model_name = "distilbert-base-uncased"
|
6 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
7 |
+
model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=2)
|
8 |
+
|
9 |
+
# Load a small dataset for fine-tuning (e.g., SST2 for sentiment analysis)
|
10 |
+
dataset = load_dataset("sst2")
|
11 |
+
def tokenize_function(examples):
|
12 |
+
return tokenizer(examples["sentence"], padding="max_length", truncation=True)
|
13 |
+
|
14 |
+
# Tokenize the dataset
|
15 |
+
tokenized_datasets = dataset.map(tokenize_function, batched=True)
|
16 |
+
|
17 |
+
# Define training arguments
|
18 |
+
training_args = TrainingArguments(
|
19 |
+
output_dir="./results",
|
20 |
+
evaluation_strategy="epoch",
|
21 |
+
logging_dir="./logs",
|
22 |
+
num_train_epochs=1,
|
23 |
+
per_device_train_batch_size=8,
|
24 |
+
per_device_eval_batch_size=8,
|
25 |
+
)
|
26 |
+
|
27 |
+
# Create Trainer instance
|
28 |
+
trainer = Trainer(
|
29 |
+
model=model,
|
30 |
+
args=training_args,
|
31 |
+
train_dataset=tokenized_datasets["train"].shuffle(seed=42).select(range(1000)), # Use a small subset for training
|
32 |
+
eval_dataset=tokenized_datasets["validation"].select(range(100)),
|
33 |
+
)
|
34 |
+
|
35 |
+
# Train the model
|
36 |
+
trainer.train()
|
37 |
+
|
38 |
+
# Save the trained model
|
39 |
+
model.save_pretrained("my-small-model")
|
40 |
+
tokenizer.save_pretrained("my-small-model")
|