Quantization made by Richard Erkhov.

Sailor-4B-Chat - GGUF

Model creator: https://huggingface.co/sail/
Original model: https://huggingface.co/sail/Sailor-4B-Chat/

Name	Quant method	Size
Sailor-4B-Chat.Q2_K.gguf	Q2_K	1.51GB
Sailor-4B-Chat.IQ3_XS.gguf	IQ3_XS	1.66GB
Sailor-4B-Chat.IQ3_S.gguf	IQ3_S	1.73GB
Sailor-4B-Chat.Q3_K_S.gguf	Q3_K_S	1.73GB
Sailor-4B-Chat.IQ3_M.gguf	IQ3_M	1.81GB
Sailor-4B-Chat.Q3_K.gguf	Q3_K	1.89GB
Sailor-4B-Chat.Q3_K_M.gguf	Q3_K_M	1.89GB
Sailor-4B-Chat.Q3_K_L.gguf	Q3_K_L	2.03GB
Sailor-4B-Chat.IQ4_XS.gguf	IQ4_XS	2.08GB
Sailor-4B-Chat.Q4_0.gguf	Q4_0	2.17GB
Sailor-4B-Chat.IQ4_NL.gguf	IQ4_NL	2.18GB
Sailor-4B-Chat.Q4_K_S.gguf	Q4_K_S	2.18GB
Sailor-4B-Chat.Q4_K.gguf	Q4_K	2.29GB
Sailor-4B-Chat.Q4_K_M.gguf	Q4_K_M	2.29GB
Sailor-4B-Chat.Q4_1.gguf	Q4_1	2.38GB
Sailor-4B-Chat.Q5_0.gguf	Q5_0	2.58GB
Sailor-4B-Chat.Q5_K_S.gguf	Q5_K_S	2.58GB
Sailor-4B-Chat.Q5_K.gguf	Q5_K	2.64GB
Sailor-4B-Chat.Q5_K_M.gguf	Q5_K_M	2.64GB
Sailor-4B-Chat.Q5_1.gguf	Q5_1	2.79GB
Sailor-4B-Chat.Q6_K.gguf	Q6_K	3.03GB
Sailor-4B-Chat.Q8_0.gguf	Q8_0	3.92GB

Original model description:

language: - en - zh - id - th - vi - ms - lo datasets: - CohereForAI/aya_dataset - CohereForAI/aya_collection - Open-Orca/OpenOrca tags: - multilingual - sea - sailor - sft - chat - instruction widget: - text: "如何制作烤鱼？" example_title: "Chinese" - text: "How to bake fish?" example_title: "English" - text: "Bagaimana cara memanggang ikan?" example_title: "Malay" - text: "วิธีย่างปลา?" example_title: "Thai" - text: "Bagaimana membuat bakaran ikan?" example_title: "Indonesian" - text: "Làm thế nào để nướng cá?" example_title: "Vietnamese" license: apache-2.0 base_model: sail/Sailor-4B inference: false

Sailor is a suite of Open Language Models tailored for South-East Asia (SEA), focusing on languages such as 🇮🇩Indonesian, 🇹🇭Thai, 🇻🇳Vietnamese, 🇲🇾Malay, and 🇱🇦Lao. Developed with careful data curation, Sailor models are designed to understand and generate text across diverse linguistic landscapes of SEA region. Built from Qwen 1.5 , Sailor encompasses models of varying sizes, spanning from 0.5B to 14B versions for different requirements. We further fine-tune the base model with open-source datasets to get instruction-tuned models, namedly Sailor-Chat. Benchmarking results demonstrate Sailor's proficiency in tasks such as question answering, commonsense reasoning, and other tasks in SEA languages.

The logo was generated by MidJourney

Model Summary

Model Collections: Base Model & Chat Model
Project Website: sailorllm.github.io
Codebase: github.com/sail-sg/sailor-llm
Technical Report: arxiv.org/pdf/2404.03608.pdf

Training details

Sailor is crafted by continually pre-training from language models like the remarkable Qwen 1.5 models, which already has a great performance on SEA languages. The pre-training corpus heavily leverages the publicly available corpus, including SlimPajama, SkyPile, CC100 and MADLAD-400. The instruction tuning corpus are all publicly available including aya_collection, aya_dataset, OpenOrca.

By employing aggressive data deduplication and careful data cleaning on the collected corpus, we have attained a high-quality dataset spanning various languages. Through systematic experiments to determine the weights of different languages, Sailor models undergo training from 200B to 400B tokens, tailored to different model sizes. The approach boosts their performance on SEA languages while maintaining proficiency in English and Chinese without significant compromise. Finally, we continually pre-train the Qwen1.5-0.5B model with 400 Billion tokens, and other models with 200 Billion tokens to obtain the Sailor models.

Requirements

The code of Sailor has been in the latest Hugging face transformers and we advise you to install transformers>=4.37.0.

Quickstart

Here provides a code snippet to show you how to load the tokenizer and model and how to generate contents.

from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda"

model = AutoModelForCausalLM.from_pretrained(
    'sail/Sailor-4B-Chat',
    torch_dtype="auto",
    device_map="auto"
)

tokenizer = AutoTokenizer.from_pretrained('sail/Sailor-4B-Chat')
system_prompt= 'You are a helpful assistant'

prompt = "Beri saya pengenalan singkat tentang model bahasa besar."
# prompt = "Hãy cho tôi một giới thiệu ngắn gọn về mô hình ngôn ngữ lớn."
# prompt = "ให้ฉันแนะนำสั้น ๆ เกี่ยวกับโมเดลภาษาขนาดใหญ่"

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "question", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

model_inputs = tokenizer([text], return_tensors="pt").to(device)
input_ids = model_inputs.input_ids.to(device)

generated_ids = model.generate(
    input_ids,
    max_new_tokens=512,
)

generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

License

Sailor is distributed under the terms of the Apache License 2.0. No restrict on the research and the commercial use, but should comply with the Qwen License.

Citation

If you find sailor useful, please cite our work as follows:

@article{dou2024sailor,
  title={Sailor: Open Language Models for South-East Asia},
  author={Dou, Longxu and Liu, Qian and Zeng, Guangtao and Guo, Jia and Zhou, Jiahui and Lu, Wei and Lin, Min},
  journal={arXiv preprint arXiv:2404.03608},
  year={2024}
}

Contact Us

If you have any questions, please raise an issue or contact us at [email protected] or [email protected].