Instructions to use RichardErkhov/sail_-_Sailor-0.5B-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RichardErkhov/sail_-_Sailor-0.5B-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="RichardErkhov/sail_-_Sailor-0.5B-gguf",
	filename="Sailor-0.5B.IQ3_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use RichardErkhov/sail_-_Sailor-0.5B-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf RichardErkhov/sail_-_Sailor-0.5B-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf RichardErkhov/sail_-_Sailor-0.5B-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf RichardErkhov/sail_-_Sailor-0.5B-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf RichardErkhov/sail_-_Sailor-0.5B-gguf:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf RichardErkhov/sail_-_Sailor-0.5B-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RichardErkhov/sail_-_Sailor-0.5B-gguf:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf RichardErkhov/sail_-_Sailor-0.5B-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RichardErkhov/sail_-_Sailor-0.5B-gguf:Q4_K_M

Use Docker

docker model run hf.co/RichardErkhov/sail_-_Sailor-0.5B-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use RichardErkhov/sail_-_Sailor-0.5B-gguf with Ollama:
```
ollama run hf.co/RichardErkhov/sail_-_Sailor-0.5B-gguf:Q4_K_M
```

Unsloth Studio

How to use RichardErkhov/sail_-_Sailor-0.5B-gguf with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for RichardErkhov/sail_-_Sailor-0.5B-gguf to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for RichardErkhov/sail_-_Sailor-0.5B-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RichardErkhov/sail_-_Sailor-0.5B-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use RichardErkhov/sail_-_Sailor-0.5B-gguf with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/sail_-_Sailor-0.5B-gguf:Q4_K_M
```

Lemonade

How to use RichardErkhov/sail_-_Sailor-0.5B-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RichardErkhov/sail_-_Sailor-0.5B-gguf:Q4_K_M

Run and chat with the model

lemonade run user.sail_-_Sailor-0.5B-gguf-Q4_K_M

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Sailor-0.5B - GGUF

Model creator: https://huggingface.co/sail/
Original model: https://huggingface.co/sail/Sailor-0.5B/

Name	Quant method	Size
Sailor-0.5B.Q2_K.gguf	Q2_K	0.28GB
Sailor-0.5B.IQ3_XS.gguf	IQ3_XS	0.3GB
Sailor-0.5B.IQ3_S.gguf	IQ3_S	0.31GB
Sailor-0.5B.Q3_K_S.gguf	Q3_K_S	0.31GB
Sailor-0.5B.IQ3_M.gguf	IQ3_M	0.32GB
Sailor-0.5B.Q3_K.gguf	Q3_K	0.33GB
Sailor-0.5B.Q3_K_M.gguf	Q3_K_M	0.33GB
Sailor-0.5B.Q3_K_L.gguf	Q3_K_L	0.34GB
Sailor-0.5B.IQ4_XS.gguf	IQ4_XS	0.36GB
Sailor-0.5B.Q4_0.gguf	Q4_0	0.37GB
Sailor-0.5B.IQ4_NL.gguf	IQ4_NL	0.37GB
Sailor-0.5B.Q4_K_S.gguf	Q4_K_S	0.37GB
Sailor-0.5B.Q4_K.gguf	Q4_K	0.38GB
Sailor-0.5B.Q4_K_M.gguf	Q4_K_M	0.38GB
Sailor-0.5B.Q4_1.gguf	Q4_1	0.39GB
Sailor-0.5B.Q5_0.gguf	Q5_0	0.42GB
Sailor-0.5B.Q5_K_S.gguf	Q5_K_S	0.42GB
Sailor-0.5B.Q5_K.gguf	Q5_K	0.43GB
Sailor-0.5B.Q5_K_M.gguf	Q5_K_M	0.43GB
Sailor-0.5B.Q5_1.gguf	Q5_1	0.45GB
Sailor-0.5B.Q6_K.gguf	Q6_K	0.48GB
Sailor-0.5B.Q8_0.gguf	Q8_0	0.62GB

Original model description:

language: - en - zh - id - th - vi - ms - lo datasets: - cerebras/SlimPajama-627B - Skywork/SkyPile-150B - allenai/MADLAD-400 - cc100 tags: - multilingual - sea - sailor license: apache-2.0 base_model: Qwen/Qwen1.5-0.5B inference: false model-index: - name: Sailor-0.5B results: - task: type: text-generation dataset: name: XQuAD-Thai type: XQuAD-Thai metrics: - name: EM (3-Shot) type: EM (3-Shot) value: 15.84 - name: F1 (3-Shot) type: F1 (3-Shot) value: 27.58 - task: type: text-generation dataset: name: TyDiQA-Indonesian type: TyDiQA-Indonesian metrics: - name: EM (3-Shot) type: EM (3-Shot) value: 30.44 - name: F1 (3-Shot) type: F1 (3-Shot) value: 54.74 - task: type: text-generation dataset: name: XQuAD-Vietnamese type: XQuAD-Vietnamese metrics: - name: EM (3-Shot) type: EM (3-Shot) value: 21.13 - name: F1 (3-Shot) type: F1 (3-Shot) value: 40.57 - task: type: text-generation dataset: name: XCOPA-Thai type: XCOPA-Thai metrics: - name: EM (3-Shot) type: EM (3-Shot) value: 51.00 - task: type: text-generation dataset: name: XCOPA-Indonesian type: XCOPA-Indonesian metrics: - name: EM (3-Shot) type: EM (3-Shot) value: 58.20 - task: type: text-generation dataset: name: XCOPA-Vietnamese type: XCOPA-Vietnamese metrics: - name: EM (3-Shot) type: EM (3-Shot) value: 58.00 - task: type: text-generation dataset: name: M3Exam-Thai type: M3Exam-Thai metrics: - name: EM (3-Shot) type: EM (3-Shot) value: 24.41 - task: type: text-generation dataset: name: M3Exam-Indonesian type: M3Exam-Indonesian metrics: - name: EM (3-Shot) type: EM (3-Shot) value: 26.15 - task: type: text-generation dataset: name: M3Exam-Vietnamese type: M3Exam-Vietnamese metrics: - name: EM (3-Shot) type: EM (3-Shot) value: 30.91 - task: type: text-generation dataset: name: BELEBELE-Thai type: BELEBELE-Thai metrics: - name: EM (3-Shot) type: EM (3-Shot) value: 32.22 - task: type: text-generation dataset: name: BELEBELE-Indonesian type: BELEBELE-Indonesian metrics: - name: EM (3-Shot) type: EM (3-Shot) value: 30.89 - task: type: text-generation dataset: name: BELEBELE-Vietnamese type: BELEBELE-Vietnamese metrics: - name: EM (3-Shot) type: EM (3-Shot) value: 32.33

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 7B 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.

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" # the device to load the model

model = AutoModelForCausalLM.from_pretrained("sail/Sailor-0.5B", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("sail/Sailor-0.5B")

input_message = "Model bahasa adalah model probabilistik" 
### The given Indonesian input translates to 'A language model is a probabilistic model of.'

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

generated_ids = model.generate(
    model_inputs.input_ids,
    max_new_tokens=64
)

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:

@misc{dou2024sailor,
      title={Sailor: Open Language Models for South-East Asia}, 
      author={Longxu Dou and Qian Liu and Guangtao Zeng and Jia Guo and Jiahui Zhou and Wei Lu and Min Lin},
      year={2024},
      eprint={2404.03608},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Contact Us

If you have any questions, please raise an issue or contact us at doulx@sea.com or liuqian@sea.com.

Downloads last month: 56

GGUF

Model size

0.6B params

Architecture

qwen2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for RichardErkhov/sail_-_Sailor-0.5B-gguf

Sailor: Open Language Models for South-East Asia

Paper • 2404.03608 • Published Apr 4, 2024 • 21