app.py

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


title = "EZChat"
description = "A State-of-the-Art Large-scale Pretrained Response generation model Qwen's 7B-Chat"
examples = [["How are you?"]]


tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True).eval()
model.generation_config = GenerationConfig.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True) # Different generation length, top_p and other related super parameters can be specified.


def predict(input, history=[]):
    # tokenize the new input sentence
    new_user_input_ids = tokenizer.encode(
    if input is not None and tokenizer.eos_token is not None:
        combined_input = input + tokenizer.eos_token
        # Rest of your code using combined_input
    else:
        # Handle the case where input or tokenizer.eos_token is None
    print("Input or eos_token is None. Cannot concatenate.")
    )

    # append the new user input tokens to the chat history
    bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)

    # generate a response
    history = model.generate(
        bot_input_ids, max_length=20, pad_token_id=tokenizer.eos_token_id
    ).tolist()

    # convert the tokens to text, and then split the responses into lines
    response = tokenizer.decode(history[0]).split("<|endoftext|>")
    # print('decoded_response-->>'+str(response))
    response = [
        (response[i], response[i + 1]) for i in range(0, len(response) - 1, 2)
    ]  # convert to tuples of list
    # print('response-->>'+str(response))
    return response, history


gr.Interface(
    fn=predict,
    title=title,
    description=description,
    examples=examples,
    inputs=["text", "state"],
    outputs=["chatbot", "state"],
    theme="ParityError/Anime",
).launch()