app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

# it is a 46.7B params llm model.

model_id = "mistralai/Mixtral-8x7B-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)

model = AutoModelForCausalLM.from_pretrained(model_id)

text = "Hello my name is"
inputs = tokenizer(text, return_tensors="pt")

outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))


def greet(name):
    # it is a 46.7B params llm model.

    model_id = "mistralai/Mixtral-8x7B-v0.1"
    tokenizer = AutoTokenizer.from_pretrained(model_id)

    model = AutoModelForCausalLM.from_pretrained(model_id)

    text = name #"Hello my name is"
    inputs = tokenizer(text, return_tensors="pt")

    outputs = model.generate(**inputs, max_new_tokens=20)
    #print(tokenizer.decode(outputs[0], skip_special_tokens=True))

    return tokenizer.decode(outputs[0], skip_special_tokens) #="Hello " + name + "!!"

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