import gradio as gr
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig,BitsAndBytesConfig

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0", trust_remote_code=True)

generation_config = GenerationConfig(
    penalty_alpha=0.6,
    do_sample = True,
    top_k=5,
    temperature=0.5,
    repetition_penalty=1.2,
    max_new_tokens=500,
    pad_token_id=tokenizer.eos_token_id
)

def generate_text(input):
    input_text = f'<|system|>\n You are a chatbot who can help code!</s> \n <|user|> \n {input} \n <|assistant|> \n'
    input_ids = tokenizer.encode(input_text, return_tensors="pt").to(device)
    output_ids = model.generate(input_ids, generation_config=generation_config)
    output_text = tokenizer.decode(output_ids[0],skip_special_tokens=True)
    return output_text

    
iface = gr.Interface(fn=generate_text, inputs="text", outputs="text")
iface.launch()