File size: 2,259 Bytes
b9cf68a
 
 
 
 
4d35d17
b9cf68a
 
 
 
 
 
 
 
 
 
 
 
4d35d17
b9cf68a
4d35d17
b9cf68a
4d35d17
 
 
 
 
b9cf68a
 
 
 
 
4d35d17
b9cf68a
 
 
4d35d17
 
 
b9cf68a
 
 
 
 
 
 
 
 
 
 
 
 
4d35d17
 
 
b9cf68a
 
 
 
 
 
 
 
 
 
 
 
 
 
4d35d17
b9cf68a
 
 
4d35d17
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
import gradio as gr
from datasets import Dataset
from transformers import AutoModelForCausalLM, AutoTokenizer, TrainingArguments, Trainer
import pandas as pd
from huggingface_hub import login
import torch

def train_model(file, hf_token):
    try:
        # Login to Hugging Face
        if not hf_token:
            return "Please provide a Hugging Face token"
        login(hf_token)
        
        # Load and prepare data
        df = pd.read_csv(file.name)
        dataset = Dataset.from_pandas(df)
        
        # Model setup - force CPU
        model_name = "facebook/opt-125m"
        device_map = "cpu"  # Force CPU usage
        tokenizer = AutoTokenizer.from_pretrained(model_name)
        model = AutoModelForCausalLM.from_pretrained(
            model_name, 
            device_map=device_map,
            torch_dtype=torch.float32  # Use float32 for CPU
        )
        
        # Training configuration
        training_args = TrainingArguments(
            output_dir="./results",
            num_train_epochs=3,
            per_device_train_batch_size=1,  # Reduced for CPU
            learning_rate=3e-5,
            save_strategy="epoch",
            push_to_hub=True,
            hub_token=hf_token,
            no_cuda=True,  # Force CPU usage
            report_to="none"  # Disable wandb logging
        )
        
        # Initialize trainer
        trainer = Trainer(
            model=model,
            args=training_args,
            train_dataset=dataset,
            tokenizer=tokenizer
        )
        
        # Run training
        trainer.train()
        
        # Push to hub
        model.push_to_hub(f"cheberle/product-classifier-{pd.Timestamp.now().strftime('%Y%m%d')}")
        
        return "Training completed successfully!"
        
    except Exception as e:
        return f"Error occurred: {str(e)}"

# Create Gradio interface
demo = gr.Interface(
    fn=train_model,
    inputs=[
        gr.File(label="Upload your CSV file"),
        gr.Textbox(label="Hugging Face Token", type="password")
    ],
    outputs="text",
    title="Product Classifier Training",
    description="Upload your CSV data to train a product classifier model on CPU."
)

if __name__ == "__main__":
    demo.launch(share=False)