Siddharth63/

Qwen3-8B-Base-4bits-AutoRound-asym

!pip install --upgrade auto-round transformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
from auto_round import AutoRoundConfig  ## must import for auto-round format

quantized_model_path = "Siddharth63/Qwen3-8B-Base-4bit-Autoround-asym"
quantization_config = AutoRoundConfig(backend="auto")
model = AutoModelForCausalLM.from_pretrained(quantized_model_path, device_map="auto",
                                             torch_dtype=torch.float16,
                                             quantization_config=quantization_config)
tokenizer = AutoTokenizer.from_pretrained(quantized_model_path)
text = "Atherosclerosis"
inputs = tokenizer(text, return_tensors="pt").to(model.device)
print(tokenizer.decode(model.generate(**inputs, max_new_tokens=50)[0]))