metadata

license: mit
datasets:
  - Vezora/Tested-143k-Python-Alpaca
language:
  - en
pipeline_tag: text2text-generation
tags:
  - code
inference:
  parameters:
    max_new_tokens: 100
    do_sample: false
widget:
  - text: >-
      <start_of_turn>user based on given instruction create a solution\n\nhere
      are the instruction Generate a Python program to reverse the order of
      words in a sentence but keep the order of the characters in each word the
      same.<end_of_turn>\n<start_of_turn>model

Gemma-2B Fine-Tuned Python Model

Overview

Gemma-2B Fine-Tuned Python Model is a deep learning model based on the Gemma-2B architecture, fine-tuned specifically for Python programming tasks. This model is designed to understand Python code and assist developers by providing suggestions, completing code snippets, or offering corrections to improve code quality and efficiency.

Model Details

Model Name: Gemma-2B Fine-Tuned Python Model
Model Type: Deep Learning Model
Base Model: Gemma-2B
Language: Python
Task: Python Code Understanding and Assistance

Example Use Cases

Code completion: Automatically completing code snippets based on partial inputs.
Syntax correction: Identifying and suggesting corrections for syntax errors in Python code.
Code quality improvement: Providing suggestions to enhance code readability, efficiency, and maintainability.
Debugging assistance: Offering insights and suggestions to debug Python code by identifying potential errors or inefficiencies.

How to Use

Install Gemma Python Package:
```
pip install transformers
```

Inference

query = input('enter a query:')
prompt_template = """
<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)

model_inputs = encodeds.to('cuda')

# Increase max_new_tokens if needed
generated_ids = merged_model.generate(**model_inputs, max_new_tokens=1000, do_sample=False, pad_token_id=tokenizer.eos_token_id)
output = ''
for i in tokenizer.decode(generated_ids[0], skip_special_tokens=True).split('<end_of_turn>')[:2]:# extracting mmodel response
    ans+=i 
cleaned_output = output.replace('<start_of_turn>', '')
print(cleaned_output)