sail/Sailor-7B-Chat-gguf

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.

GGUF model list

Name	Quant method	Bits	Size	Use case
ggml-model-Q2_K.gguf	Q2_K	2	3.10 GB	medium, significant quality loss
ggml-model-Q3_K_L.gguf	Q3_K_L	3	4.22 GB	large, substantial quality loss
ggml-model-Q3_K_M.gguf	Q3_K_M	3	3.92 GB	medium, balanced quality
ggml-model-Q3_K_S.gguf	Q3_K_S	3	3.57 GB	medium, high quality loss
ggml-model-Q4_K_M.gguf	Q4_K_M	4	4.77 GB	large, balanced quality
ggml-model-Q4_K_S.gguf	Q4_K_S	4	4.54 GB	large, greater quality loss
ggml-model-Q5_K_M.gguf	Q5_K_M	5	5.53 GB	large, balanced quality
ggml-model-Q5_K_S.gguf	Q5_K_S	5	5.4 GB	large, very low quality loss
ggml-model-Q6_K.gguf	Q6_K	6	6.34 GB	large, extremely low quality loss
ggml-model-Q8_0.gguf	Q8_0	8	8.21 GB	very large, extremely low quality loss
ggml-model-f16.gguf	f16	16	15.40 GB	very large, no quality loss

How to run with llama.cpp

# install llama.cpp
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
make
pip install -r requirements.txt

# generate with llama.cpp
./main -ngl 32 -m ggml-model-Q4_K_M.gguf -p "<|im_start|>question\nCara memanggang ikan?\n<|im_start|>answer\n" --temp 0.7 --repeat_penalty 1.1 -n 400 -e

Change -ngl 32 to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.

How to run with llama-cpp-python

pip install llama-cpp-python

import llama_cpp
import llama_cpp.llama_tokenizer

# load model
llama = llama_cpp.Llama.from_pretrained(
    repo_id="sail/Sailor-4B-Chat-gguf",
    filename="ggml-model-Q4_K_M.gguf",
    tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("sail/Sailor-4B-Chat"),
    n_gpu_layers=40,
    n_threads=8,
    verbose=False,
)

system_role= 'system'
user_role = 'question'
assistant_role = "answer"

system_prompt= \
'You are an AI assistant named Sailor created by Sea AI Lab. \
Your answer should be friendly, unbiased, faithful, informative and detailed.'
system_prompt = f"<|im_start|>{system_role}\n{system_prompt}<|im_end|>"

# inference example
output = llama(
  system_prompt + '\n' + f"<|im_start|>{user_role}\nCara memanggang ikan?\n<|im_start|>{assistant_role}\n",
  max_tokens=256,
  temperature=0.7,
  top_p=0.75,
  top_k=60,
  stop=["<|im_end|>", "<|endoftext|>"]
)

print(output['choices'][0]['text'])

How to build demo

Install llama-cpp-python and gradio, then run script.

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].