app.py

from transformers import AutoTokenizer, AutoModelForCausalLM
import gradio as gr

model_id = "RWKV/rwkv-raven-1b5"

model = AutoModelForCausalLM.from_pretrained(model_id)
tokenizer = AutoTokenizer.from_pretrained(model_id)


def chat(question):
    prompt = f"### Instruction: {question}\n### Response:"

    inputs = tokenizer(prompt, return_tensors="pt")
    output = model.generate(inputs["input_ids"], max_new_tokens=100)
    
    response = tokenizer.decode(output[0].tolist(), skip_special_tokens=True)
    print(response)
    
    return response

iface = gr.Interface(fn=chat,
                     inputs=gr.inputs.Textbox(label="Enter your text"),
                     outputs="text",
                     title="Chat with Surrey County Council InfoBot")

# index = construct_index("docs")
iface.launch()