Modal vs Hugging Face

import modal

app = modal.App("my-ml-app")

image = modal.Image.debian_slim().pip_install("torch", "transformers")

@app.function(gpu="T4", image=image)
def run_inference(prompt: str) -> str:
    from transformers import pipeline
    pipe = pipeline("text-generation", model="gpt2")
    result = pipe(prompt, max_length=100)
    return result[0]['generated_text']

@app.local_entrypoint()
def main():
    output = run_inference.remote("Once upon a time")
    print(output)

import { HfInference } from '@huggingface/inference';

const hf = new HfInference(process.env.HUGGINGFACE_API_KEY);

// Text generation
const result = await hf.textGeneration({
  model: 'mistralai/Mistral-7B-Instruct-v0.3',
  inputs: 'Explain quantum computing in one sentence:',
  parameters: { max_new_tokens: 100, temperature: 0.7 },
});

console.log(result.generated_text);