app.py

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

title = "🤖AI ChatBot"
description = "A State-of-the-Art Large-scale Pretrained Response generation model (DialoGPT)"
examples = [["How are you?"]]


# Load model directly
from transformers import AutoModel
#model = AutoModel.from_pretrained("ironlanderl/gemma-2-2b-it-Q5_K_M-GGUF")
#modelName = "google/gemma-2-2b-it"
#modelName = "ironlanderl/gemma-2-2b-it-Q5_K_M-GGUF"
modelName = "bartowski/Mistral-Nemo-Instruct-2407-GGUF"
modelId = "Mistral-Nemo-Instruct-2407-Q2_K.gguf"
tokenizer = AutoTokenizer.from_pretrained(modelName,gguf_file=modelId)

model = AutoModel.from_pretrained(modelName,gguf_file=modelId,torch_dtype=torch.float16)
#model = AutoModelForCausalLM.from_pretrained("google/gemma-2-2b-it", torch_dtype=torch.float16 )
#stvlynn/Gemma-2-2b-Chinese-it
#tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large")
#model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large")
#The model was loaded with use_flash_attention_2=True, which is deprecated and may be removed in a future release. Please use `attn_implementation="flash_attention_2"` instead.

def generate_text(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(**inputs)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

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


"""
def predict(input, history=[]):
    # tokenize the new input sentence
    new_user_input_ids = tokenizer.encode(
        input + tokenizer.eos_token, return_tensors="pt"
    )
    #attentionMask = torch.ones(new_user_input_ids.shape, dtype=torch.long)
    
    # 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=4000, 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="finlaymacklon/boxy_violet",
).launch()
"""