Downloads · 30 days
37
1% of all-time downloads
typhoon-ai/typhoon-7b-instruct-02-19-2024
typhoon-7b-instruct-02-19-2024 is a text generation model from typhoon-ai. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Typhoon-0219: Thai Large Language Model (Instruct)
Downloads · 30 days
37
1% of all-time downloads
All-time downloads
3.9K
Public
Parameters
7.3B
14.5 GB on disk
Likes
2
Public
Click a slice to open those files.
.safetensors14.5 GB · 100%
From the Hugging Face model README
Typhoon-0219: Thai Large Language Model (Instruct)
Typhoon-0219 is a instruct Thai 🇹🇭 large language model with 7 billion parameters, and it is based on Typhoon 7B. It is the second-generation instruct model version that serves opentyphoon.ai. It is trained on a diverse instruction tuning dataset with more than 1 million rows, similar to OpenHermes, and supports using system prompts.
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.
We suggest using the OpenAI-compatible API server from the vLLM project.
python -m vllm.entrypoints.openai.api_server --port 8080 --model scb10x/typhoon-7b-instruct-02-19-2024 --max-num-batched-tokens 8192 --max-model-len 8192 --served-model-name typhoon-instruct
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 %}
https://twitter.com/opentyphoon
@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}
}