Typhoon-1.5-72B-instruct: Thai Large Language Model (Instruct)
Typhoon-1.5-72B-instruct is a instruct Thai 🇹🇭 large language model with 72 billion parameters, and it is based on Qwen1.5-72B.
We also have a newer release of 1.5x 70B, which is better for application use cases. here
For release post, please see our blog.
Model Description
- Model type: A 72B instruct decoder-only model based on Qwen1.5 archtecture.
- Requirement: transformers 4.38.0 or newer.
- Primary Language(s): Thai 🇹🇭 and English 🇬🇧
- License: Qwen License
Performance
| Model | ONET | IC | TGAT | TPAT-1 | A-Level | Average (ThaiExam) | M3Exam | MMLU |
|---|---|---|---|---|---|---|---|---|
| Typhoon-1.5 72B | 0.562 | 0.716 | 0.778 | 0.5 | 0.528 | 0.6168 | 0.587 | 0.7271 |
| OpenThaiGPT 1.0.0 70B | 0.447 | 0.492 | 0.778 | 0.5 | 0.319 | 0.5072 | 0.493 | 0.6167 |
| GPT-3.5-turbo(01-2024) | 0.358 | 0.279 | 0.678 | 0.345 | 0.318 | 0.3956 | 0.316 | 0.700** |
| GPT-4(04-2024) | 0.589 | 0.594 | 0.756 | 0.517 | 0.616 | 0.6144 | 0.626 | 0.864** |
| ** We report the MMLU score that is reported in GPT-4 Tech Report. |
Usage Example
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_id = "scb10x/typhoon-v1.5-72b-instruct"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
) # We do not recommend loading the model using 4-bit and 8-bit BNB as it may produce inaccurate results.
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "ขอสูตรไก่ย่าง"},
]
input_ids = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt"
).to(model.device)
outputs = model.generate(
input_ids,
max_new_tokens=1024,
do_sample=True,
temperature=0.6,
top_p=0.9,
repetition_penalty=1.15
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))
Chat Template
We use chatml chat-template.
{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content']}}{% if (loop.last and add_generation_prompt) or not loop.last %}{{ '<|im_end|>' + '\n'}}{% endif %}{% endfor %}
{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{ '<|im_start|>assistant\n' }}{% endif %}
Intended Uses & Limitations
This model is an instructional model. However, it’s still undergoing development. It incorporates some level of guardrails, but it still may produce answers that are inaccurate, biased, or otherwise objectionable in response to user prompts. We recommend that developers assess these risks in the context of their use case.
Follow us
https://twitter.com/opentyphoon
Support / Ask any question
SCB10X AI Team
- Kunat Pipatanakul, Potsawee Manakul, Sittipong Sripaisarnmongkol, Natapong Nitarach, Pathomporn Chokchainant, Kasima Tharnpipitchai
- If you find Typhoon v1.5 useful for your work, please cite it using:
@article{pipatanakul2023typhoon,
title={Typhoon: Thai Large Language Models},
author={Kunat Pipatanakul and Phatrasek Jirabovonvisut and Potsawee Manakul and Sittipong Sripaisarnmongkol and Ruangsak Patomwong and Pathomporn Chokchainant and Kasima Tharnpipitchai},
year={2023},
journal={arXiv preprint arXiv:2312.13951},
url={https://arxiv.org/abs/2312.13951}
}
Contact Us
- General & Collaboration: kasima@scb10x.com, pathomporn@scb10x.com
- Technical: kunat@scb10x.com