Mert

import time
from askui import VisionAgent

with VisionAgent() as agent:
    agent.tools.webbrowser.open_new("http://www.google.com")
    time.sleep(0.5)
    agent.click("search field in the center of the screen", model_name="Qwen/Qwen2-VL-7B-Instruct")
    agent.type("cats")
    agent.keyboard("enter")
    time.sleep(0.5)
    agent.click("text 'Images'", model_name="AskUI/PTA-1")
    time.sleep(0.5)
    agent.click("second cat image", model_name="OS-Copilot/OS-Atlas-Base-7B")

from transformers import AutoModelForSequenceClassification, Trainer, TrainingArguments
from peft import LoraConfig, get_peft_model
from datasets import load_dataset

# Loading the pre-trained BERT model
model = AutoModelForSequenceClassification.from_pretrained('bert-base-uncased', num_labels=2)

# Configuring the LoRA parameters
lora_config = LoraConfig(
    r=8,
    lora_alpha=16, 
    lora_dropout=0.1, 
    bias="none" 
)

# Applying LoRA to the model
model = get_peft_model(model, lora_config)

# Loading dataset for classification
dataset = load_dataset("glue", "sst2")
train_dataset = dataset["train"]

# Setting the training arguments
training_args = TrainingArguments(
    output_dir="./results",
    per_device_train_batch_size=16,
    num_train_epochs=3,
    logging_dir="./logs",
)

# Creating a Trainer instance for fine-tuning
trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=train_dataset,
)

# Finally we can fine-tune the model
trainer.train()