Upload quantized model Seed-Coder-8B-Base-autoround-W4A16

0533453 verified 1 day ago

4 kB

base_model:
  - ByteDance-Seed/Seed-Coder-8B-Base
pipeline_tag: text-generation
tags:
  - quantized
  - w4a16
  - autoround
  - low-bit-open-llm-leaderboard

Seed-Coder-8B-Base-autoround-W4A16

Model Details

This model is a int4 weight-only quantization with group_size 128 and symmetric quantization of ByteDance-Seed/Seed-Coder-8B-Base generated by AutoRound. Please follow the license of the original model.

Quantization Details

Attribute	Value
Base Model	ByteDance-Seed/Seed-Coder-8B-Base
Quantization Tool	AutoRound
Quantization Scheme	W4A16
Original Size	16384 MB
Quantized Size	5894 MB

Evaluation Results

Task	Accuracy
hellaswag	0.4039
mmlu	0.3810
piqa	0.6839

How to Use

HF Usage

Step 1: Install AutoRound

pip install auto-round

Step 2: Load and run the quantized model

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Seed-Coder-8B-Base-autoround-W4A16"

# 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 = "Write a quick sort algorithm."
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=512)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]) :].tolist()

content = tokenizer.decode(output_ids, skip_special_tokens=True)
print("content:", content)

VLLM Usage

vllm serve Seed-Coder-8B-Base-autoround-W4A16 \
    --trust-remote-code \
    --dtype bfloat16 \
    --tensor_parallel_size 1

If you encounter any issues, feel free to open an issue on the AutoRound GitHub repo or provide feedback on the Low-Bit Open LLM Leaderboard.

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:

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

This model is part of the Intel Low-Bit Open LLM Leaderboard initiative.