app.py

import gradio as gr
import spaces
# import torch
from huggingface_hub import hf_hub_download
from llama_cpp import Llama, LlamaGrammar


# zero = torch.Tensor([0]).cuda()
# print(f'zero.device: {zero.device}') # <-- 'cpu' 🤔

@spaces.GPU
def greet(n):
    global llm
    llm = load_model(download_model())

    # print(f'zero.device: {zero.device}') # <-- 'cuda:0' 🤗
    grammar = LlamaGrammar.from_string('''
    root ::= sentence
    answer ::= (weather | complaint | yesno | gen)
    weather ::= ("Sunny." | "Cloudy." | "Rainy.")
    complaint ::= "I don't like talking about the weather."
    yesno ::= ("Yes." | "No.")
    gen ::= "1. " [A-Z] [a-z] [a-z]*
    sentence ::= [A-Z] [A-Za-z0-9 ,-]* ("." | "!" | "?")
    ''')

    prompts = [
        "How's the weather in London?",
        "How's the weather in Munich?",
        "How's the weather in Barcelona?",
    ]

    print(f'Making a big inference...... {prompts[0]}')
    output = llm(
            prompts[0],
            max_tokens=512,
            temperature=0.4,
            grammar=grammar
    )
    print(f'Returned..... {output}')

    s = output['choices'][0]['text']
    print(f'{s} , len(s) = {len(s)}')
    print(output['choices'])
    print(output['choices'][0]['text'])
    print()

    return f"Hello {s} Tensor"

def download_model():

    REPO_ID = "TheBloke/Llama-2-7B-GGUF"
    FILENAME = "llama-2-7b.Q5_K_S.gguf"

    print(f'Downloading model {REPO_ID}/{FILENAME}')
    m = hf_hub_download(repo_id=REPO_ID, filename=FILENAME)
    print(f'status: {m}')
    return m

def load_model(fp):
    from llama_cpp import Llama, LlamaGrammar

    print(f'Loading model: {fp}')
    model_file=fp
    llm = Llama(
        model_path=model_file,
        n_gpu_layers=-1, verbose=True
    )
    return llm

demo = gr.Interface(fn=greet, inputs=gr.Number(), outputs=gr.Text())
demo.launch(share=False)