Gemma 2B Finetuined Pythoncode

🚀 Gemma-2B Fine-Tuned Python Model

A deep learning model based on the Gemma-2B architecture, fine-tuned for Python programming tasks, offering code assistance and quality improvement.

🚀 Quick Start

The Gemma-2B Fine-Tuned Python Model is a specialized deep - learning model. It's built on the Gemma - 2B architecture and fine - tuned for Python programming. This model can understand Python code and assist developers in various ways, such as providing suggestions, completing code snippets, and correcting code to enhance quality and efficiency.

✨ Features

• Code Completion: Automatically finish code snippets according to partial inputs.
• Syntax Correction: Spot and suggest fixes for syntax errors in Python code.
• Code Quality Improvement: Offer suggestions to make code more readable, efficient, and maintainable.
• Debugging Assistance: Provide insights and suggestions to debug Python code by identifying potential errors or inefficiencies.

📦 Installation

1. Install Gemma Python Package:

    pip install -q -U transformers==4.38.0
    pip install torch
   

💻 Usage Examples

Basic Usage

# Load model directly
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Mr-Vicky-01/Gemma-2B-Finetuined-pythonCode")
model = AutoModelForCausalLM.from_pretrained("Mr-Vicky-01/Gemma-2B-Finetuined-pythonCode")

query = input('enter a query:')
prompt_template = f"""
<start_of_turn>user based on given instruction create a solution\n\nhere are the instruction {query}
<end_of_turn>\n<start_of_turn>model
"""
prompt = prompt_template
encodeds = tokenizer(prompt, return_tensors="pt", add_special_tokens=True).input_ids

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)
inputs = encodeds.to(device)


# Increase max_new_tokens if needed
generated_ids = model.generate(inputs, max_new_tokens=1000, do_sample=False, pad_token_id=tokenizer.eos_token_id)
ans = ''
for i in tokenizer.decode(generated_ids[0], skip_special_tokens=True).split('<end_of_turn>')[:2]:
    ans += i

# Extract only the model's answer
model_answer = ans.split("model")[1].strip()
print(model_answer)

📚 Documentation

Model Details

📄 License

This project is licensed under the MIT License.