from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Intel/Qwen3-235B-A22B-Instruct-2507-int4-asym-AutoRound"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Give me a short introduction to large language model."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=16384
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()

content = tokenizer.decode(output_ids, skip_special_tokens=True)

print("content:", content)

"""
content: A Large Language Model (LLM) is a type of artificial intelligence designed to understand, generate, and manipulate human language. Built using deep learning techniques—especially transformer architectures—LLMs are trained on vast amounts of text data from books, websites, and other sources. This training enables them to recognize patterns in language, answer questions, write essays, translate languages, and even generate creative content like stories or code. Due to their scale—often with billions of parameters—LLMs can capture nuanced linguistic features and produce remarkably human-like text. Examples include models like GPT, Llama, and PaLM. LLMs are transforming fields such as education, customer service, and content creation by enabling more natural and intelligent interactions between humans and machines.

"""

Generate the model

Here is the sample command to reproduce the model

auto-round --model Qwen/Qwen3-235B-A22B-Instruct-2507 --output_dir ./Qwen3-235B-A22B-Instruct-2507-int4 --enable_torch_compile --format auto_round:auto_awq --asym

Ethical Considerations and Limitations

The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.

Therefore, before deploying any applications of the model, developers should perform safety testing.

Caveats and Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.

Here are a couple of useful links to learn more about Intel's AI software:

Intel Neural Compressor link

Disclaimer

The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.

Cite

@article{cheng2023optimize, title={Optimize weight rounding via signed gradient descent for the quantization of llms}, author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, journal={arXiv preprint arXiv:2309.05516}, year={2023} }

arxiv github

OPEA/Qwen3-235B-A22B-Instruct-2507-int4-asym-AutoRound

Model Details

How To Use

Generate the model

Ethical Considerations and Limitations

Caveats and Recommendations

Disclaimer

Cite

OPEA/
Qwen3-235B-A22B-Instruct-2507-int4-asym-AutoRound