Update README.md

README.md

@@ -12,4 +12,98 @@ tags:
 - sentiment-analysis
 ---
 
-## 
+```python
+# IMDB
+! pip install transformers datasets evaluate accelerate -q
+
+import evaluate
+import numpy as np
+from huggingface_hub import login
+from datasets import load_dataset, Dataset, DatasetDict
+from transformers import AutoTokenizer, DataCollatorWithPadding
+from transformers import AutoModelForSequenceClassification, TrainingArguments, Trainer
+
+# Basic fine-tuning arguments
+token="your_token"
+task="christykoh/imdb_pt"
+model_name="neuralmind/bert-base-portuguese-cased"
+output_dir="checkpoint"
+learning_rate=4e-5
+per_device_train_batch_size=32
+per_device_eval_batch_size=32
+num_train_epochs=3
+weight_decay=0.01
+evaluation_strategy="epoch"
+save_strategy="epoch"
+hub_model_id="nicholasKluge/Teeny-tiny-llama-162m-imdb"
+
+# Login on the hub to load and push
+login(token=token)
+
+# Load the task
+dataset = load_dataset(task)
+
+# Create a `ModelForSequenceClassification`
+model = AutoModelForSequenceClassification.from_pretrained(
+    model_name, 
+    num_labels=2, 
+    id2label={0: "NEGATIVE", 1: "POSITIVE"}, 
+    label2id={"NEGATIVE": 0, "POSITIVE": 1}
+)
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+# If model does not have a pad_token, we need to add it
+#tokenizer.pad_token = tokenizer._eos_token
+#model.config.pad_token_id = model.config.eos_token_id
+
+# Pre process the dataset
+def preprocess_function(examples):
+    return tokenizer(examples["text"], truncation=True, max_length=256)
+
+dataset_tokenized = dataset.map(preprocess_function, batched=True)
+
+# Create a simple data collactor
+data_collator = DataCollatorWithPadding(tokenizer=tokenizer)
+
+# Use accuracy as evaluation metric
+accuracy = evaluate.load("accuracy")
+
+# Function to compute accuracy
+def compute_metrics(eval_pred):
+    predictions, labels = eval_pred
+    predictions = np.argmax(predictions, axis=1)
+    return accuracy.compute(predictions=predictions, references=labels)
+
+# Define training arguments
+training_args = TrainingArguments(
+    output_dir=output_dir,
+    learning_rate=learning_rate,
+    per_device_train_batch_size=per_device_train_batch_size,
+    per_device_eval_batch_size=per_device_eval_batch_size,
+    num_train_epochs=num_train_epochs,
+    weight_decay=weight_decay,
+    evaluation_strategy=evaluation_strategy,
+    save_strategy=save_strategy,
+    load_best_model_at_end=True,
+    push_to_hub=False,
+    hub_token=token,
+    hub_private_repo=True,
+    hub_model_id=hub_model_id,
+    tf32=False,
+)
+
+# Define the Trainer
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=dataset_tokenized["train"],
+    eval_dataset=dataset_tokenized["test"],
+    tokenizer=tokenizer,
+    data_collator=data_collator,
+    compute_metrics=compute_metrics,
+)
+
+# Train!
+trainer.train()
+```