RichardErkhov/scb10x_-_llama-3-typhoon-v1.5-8b-gguf

Quantization made by Richard Erkhov.

llama-3-typhoon-v1.5-8b - GGUF

Model creator: https://huggingface.co/scb10x/
Original model: https://huggingface.co/scb10x/llama-3-typhoon-v1.5-8b/

Name	Quant method	Size
llama-3-typhoon-v1.5-8b.Q2_K.gguf	Q2_K	2.96GB
llama-3-typhoon-v1.5-8b.IQ3_XS.gguf	IQ3_XS	3.28GB
llama-3-typhoon-v1.5-8b.IQ3_S.gguf	IQ3_S	3.43GB
llama-3-typhoon-v1.5-8b.Q3_K_S.gguf	Q3_K_S	3.41GB
llama-3-typhoon-v1.5-8b.IQ3_M.gguf	IQ3_M	3.52GB
llama-3-typhoon-v1.5-8b.Q3_K.gguf	Q3_K	3.74GB
llama-3-typhoon-v1.5-8b.Q3_K_M.gguf	Q3_K_M	3.74GB
llama-3-typhoon-v1.5-8b.Q3_K_L.gguf	Q3_K_L	4.03GB
llama-3-typhoon-v1.5-8b.IQ4_XS.gguf	IQ4_XS	4.18GB
llama-3-typhoon-v1.5-8b.Q4_0.gguf	Q4_0	4.34GB
llama-3-typhoon-v1.5-8b.IQ4_NL.gguf	IQ4_NL	4.38GB
llama-3-typhoon-v1.5-8b.Q4_K_S.gguf	Q4_K_S	4.37GB
llama-3-typhoon-v1.5-8b.Q4_K.gguf	Q4_K	4.58GB
llama-3-typhoon-v1.5-8b.Q4_K_M.gguf	Q4_K_M	4.58GB
llama-3-typhoon-v1.5-8b.Q4_1.gguf	Q4_1	4.78GB
llama-3-typhoon-v1.5-8b.Q5_0.gguf	Q5_0	5.21GB
llama-3-typhoon-v1.5-8b.Q5_K_S.gguf	Q5_K_S	5.21GB
llama-3-typhoon-v1.5-8b.Q5_K.gguf	Q5_K	5.34GB
llama-3-typhoon-v1.5-8b.Q5_K_M.gguf	Q5_K_M	5.34GB
llama-3-typhoon-v1.5-8b.Q5_1.gguf	Q5_1	5.65GB
llama-3-typhoon-v1.5-8b.Q6_K.gguf	Q6_K	6.14GB
llama-3-typhoon-v1.5-8b.Q8_0.gguf	Q8_0	7.95GB

Original model description:

license: llama3 language: - th - en pipeline_tag: text-generation tags: - pretrained

Llama-3-Typhoon-v1.5-8B: Thai Large Language Model (Pretrained)

Typhoon-8B is a pretrained only Thai 🇹🇭 large language model with 8 billion parameters, and it is based on Llama3-8B.

For release notes, please see our blog. *To acknowledge Meta's effort in creating the foundation model and to comply with the license, we explicitly include "llama-3" in the model name.

Model Description

Model type: A 8B pretrained decoder-only model based on Llama architecture.
Requirement: transformers 4.38.0 or newer.
Primary Language(s): Thai 🇹🇭 and English 🇬🇧
License: Llama 3 Community License

Intended Uses & Limitations

This model is a pretrained base model. Thus, it may not be able to follow human instructions without using one/few-shot learning or instruction fine-tuning. The model does not have any moderation mechanisms, and may generate harmful or inappropriate responses.

https://twitter.com/opentyphoon

Support

https://discord.gg/CqyBscMFpg

SCB10X AI Team

Kunat Pipatanakul, Potsawee Manakul, Sittipong Sripaisarnmongkol, Natapong Nitarach, Pathomporn Chokchainant, Kasima Tharnpipitchai
If you find Typhoon-8B 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

RichardErkhov
/

scb10x_-_llama-3-typhoon-v1.5-8b-gguf