index.html

<h2>Usage</h2>

<p>You can load models using the Hugging Face Transformers library:</p>

<p style="background-color: gray">
from transformers import pipeline

pipe = pipeline("text-generation", model="nroggendorff/mayo")

question = "What color is the sky?"
conv = [{"role": "user", "content": question}]

response = pipe(conv, max_new_tokens=32)[0]['generated_text'][-1]['content']
print(response)
</p>

<p>To use models with quantization:</p>

<p style="background-color: gray">
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
import torch

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_use_double_quant=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16
)

model_id = "nroggendorff/mayo"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config)

question = "What color is the sky?"
prompt = tokenizer.apply_chat_template([{"role": "user", "content": question}], tokenize=False)
inputs = tokenizer(prompt, return_tensors="pt")

outputs = model.generate(**inputs, max_new_tokens=32)

generated_text = tokenizer.batch_decode(outputs)[0]
print(generated_text)
</p>