Finetuned Gemma LLM

A Finetuned Large Language Model specifically trained on datasets of python codes to teach python and help developers in debugging.

Model Link

Run Model on Google Colab CPU

• Create read access token on Hugging Face [Here]

Install transformers library

pip install transformers

Use LLM on Google Colab to Generate Code

from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "shahdishank/gemma-2b-it-finetune-python-codes"
HUGGING_FACE_TOKEN = "YOUR_TOKEN"
tokenizer = AutoTokenizer.from_pretrained(model_name, token="HUGGING_FACE_TOKEN")
model = AutoModelForCausalLM.from_pretrained(model_name, token="HUGGING_FACE_TOKEN")

prompt_template = """\
  user:\n{query} \n\n assistant:\n
  """
prompt = prompt_template.format(query="write a simple python function") # write your query here

input_ids = tokenizer(prompt, return_tensors="pt", add_special_tokens=True)
outputs = model.generate(**input_ids, max_new_tokens=2000, do_sample=True, pad_token_id=tokenizer.eos_token_id)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Output on Google Colab Screenshot

Features

• Code generation
• Debugging
• Learn and understand various python coding styles

Tech Stack

Language: Python

Library: transformers, PEFT

LLM: Gemma-2b-it

IDE: Google Colab

Resources Used

• Base Model:
  • Gemma Model Docs
  • Gemma Model from Hugging Face
• Dataset:
  • python-codes-25k

Feedback

If you have any feedback, please reach out to me at [email protected]

Author

• @shahdishank