app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline

model_id = "codellama/CodeLlama-34b-hf"  # You can change to 13b or 34b if you have the hardware

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype="auto")

pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

def generate_code(prompt):
    output = pipe(prompt, max_new_tokens=200, do_sample=True, temperature=0.7)
    return output[0]["generated_text"]

gr.Interface(fn=generate_code, inputs="text", outputs="text", title="Code Llama Playground").launch()