Model Details

This model is an int4 model with group_size 128 and symmetric quantization of tencent/Youtu-LLM-2B generated by intel/auto-round. Please follow the license of the original model.

How to Use

HF Usage

# transformers==4.57.1
import re
from transformers import AutoTokenizer, AutoModelForCausalLM

# 1. Configure Model
model_id = "Intel/Youtu-LLM-2B-int4-AutoRound"

# 2. Initialize Tokenizer and Model
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    trust_remote_code=True
)

# 3. Construct Dialogue Input
prompt = "Hello"
messages = [{"role": "user", "content": prompt}]

# Use apply_chat_template to construct input; set enable_thinking=True to activate Reasoning Mode
input_text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True
)

model_inputs = tokenizer([input_text], return_tensors="pt").to(model.device)
print("Input prepared. Starting generation...")

# 4. Generate Response
outputs = model.generate(
    **model_inputs,
    max_new_tokens=512,
    do_sample=True,
    temperature=1.0,
    top_k=20,
    top_p=0.95,
    repetition_penalty=1.05
)
print("Generation complete!")

# 5. Parse Results
full_response = tokenizer.decode(outputs[0], skip_special_tokens=True)

def parse_reasoning(text):
    """Extract thought process within <think> tags and the subsequent answer content"""
    thought_pattern = r"<think>(.*?)</think>"
    match = re.search(thought_pattern, text, re.DOTALL)
    
    if match:
        thought = match.group(1).strip()
        answer = text.split("</think>")[-1].strip()
    else:
        thought = "(No explicit thought process generated)"
        answer = text
    return thought, answer

thought, final_answer = parse_reasoning(full_response)

print(f"\n{'='*20} Thought Process {'='*20}\n{thought}")
print(f"\n{'='*20} Final Answer {'='*20}\n{final_answer}")

Generate the Model

pip install transformers==4.57.1
auto-round --bits 4 --iters 200 --model_name tencent/Youtu-LLM-2B

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

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