app.py

# Import required libraries
import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the model and tokenizer
MODEL_NAME = "SeaLLMs/SeaLLM-7B-v2.5"

# Download model and tokenizer from Hugging Face
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype="auto", device_map="auto")

# Define the chatbot function
def chatbot(user_input):
    inputs = tokenizer(user_input, return_tensors="pt").to("cuda")
    outputs = model.generate(inputs["input_ids"], max_length=150, num_return_sequences=1, temperature=0.7)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

# Create a Gradio interface
interface = gr.Interface(
    fn=chatbot,
    inputs="text",
    outputs="text",
    title="SeaLLM Chatbot",
    description="A chatbot powered by SeaLLM-7B-v2.5.",
    examples=["Hello!", "What's the weather today?", "Tell me a joke!"],
)

# Launch the interface
if __name__ == "__main__":
    interface.launch()