Llama-3.2-1B-Instruct-SparseGPT-INT4

Llama 3.2 (1B) Instruct quantized using SparseGPT (4-bit)

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Almheiri/Llama-3.2-1B-Instruct-SparseGPT-INT4"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")

prompt = [
  {"role": "system", "content": "You are a helpful assistant, that responds as a pirate."},
  {"role": "user", "content": "What's Deep Learning?"},
]
inputs = tokenizer.apply_chat_template(
  prompt,
  tokenize=True,
  add_generation_prompt=True,
  return_tensors="pt",
  return_dict=True,
).to("cuda")

outputs = model.generate(**inputs, do_sample=True, max_new_tokens=256)
print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0].split("assistant")[-1])