@inproceedings{wang-etal-2024-telechat,
title = "{T}ele{C}hat: An Open-source Billingual Large Language Model",
author = "Wang, Zihan and
Liuxz2@chinatelecom.cn, Liuxz2@chinatelecom.cn and
Liusx14@chinatelecom.cn, Liusx14@chinatelecom.cn and
Yao, Yitong and
Huangyy121@chinatelecom.cn, Huangyy121@chinatelecom.cn and
Mengxiang, Li and
He, Zhongjiang and
Liyx25@chinatelecom.cn, Liyx25@chinatelecom.cn and
Pulw@chinatelecom.cn, Pulw@chinatelecom.cn and
Xuhn@chinatelecom.cn, Xuhn@chinatelecom.cn and
Wang, Chao and
Song, Shuangyong",
editor = "Wong, Kam-Fai and
Zhang, Min and
Xu, Ruifeng and
Li, Jing and
Wei, Zhongyu and
Gui, Lin and
Liang, Bin and
Zhao, Runcong",
booktitle = "Proceedings of the 10th SIGHAN Workshop on Chinese Language Processing (SIGHAN-10)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.sighan-1.2",
pages = "10--20",
abstract = "In this paper, we present \textbf{TeleChat}, a collection of large language models (LLMs) with parameters of 7 billion and 12 billion. TeleChat is initially pretrained on an extensive corpus containing a diverse collection of texts from both English and Chinese languages, encompassing trillions of tokens. Subsequently, the model undergoes fine-tuning to align with human preferences, following a detailed methodology that we describe. We evaluate the performance of TeleChat on various tasks, including general dialogue generation, language understanding, mathematics, reasoning, code generation, and knowledge-based question answering. Our findings indicate that TeleChat achieves state-of-the-art performance to other open-source models of similar size across a wide range of public benchmarks. To support future research and applications utilizing LLMs, we release the fine-tuned model checkpoints of TeleChat-7B and TeleChat-12B, along with code and a portion of our filtered high-quality pretraining data, to the public community.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2024-telechat">
<titleInfo>
<title>TeleChat: An Open-source Billingual Large Language Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zihan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liuxz2@chinatelecom.cn</namePart>
<namePart type="family">Liuxz2@chinatelecom.cn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liusx14@chinatelecom.cn</namePart>
<namePart type="family">Liusx14@chinatelecom.cn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yitong</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huangyy121@chinatelecom.cn</namePart>
<namePart type="family">Huangyy121@chinatelecom.cn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Mengxiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongjiang</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liyx25@chinatelecom.cn</namePart>
<namePart type="family">Liyx25@chinatelecom.cn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pulw@chinatelecom.cn</namePart>
<namePart type="family">Pulw@chinatelecom.cn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuhn@chinatelecom.cn</namePart>
<namePart type="family">Xuhn@chinatelecom.cn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuangyong</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th SIGHAN Workshop on Chinese Language Processing (SIGHAN-10)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kam-Fai</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongyu</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lin</namePart>
<namePart type="family">Gui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Runcong</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present TeleChat, a collection of large language models (LLMs) with parameters of 7 billion and 12 billion. TeleChat is initially pretrained on an extensive corpus containing a diverse collection of texts from both English and Chinese languages, encompassing trillions of tokens. Subsequently, the model undergoes fine-tuning to align with human preferences, following a detailed methodology that we describe. We evaluate the performance of TeleChat on various tasks, including general dialogue generation, language understanding, mathematics, reasoning, code generation, and knowledge-based question answering. Our findings indicate that TeleChat achieves state-of-the-art performance to other open-source models of similar size across a wide range of public benchmarks. To support future research and applications utilizing LLMs, we release the fine-tuned model checkpoints of TeleChat-7B and TeleChat-12B, along with code and a portion of our filtered high-quality pretraining data, to the public community.</abstract>
<identifier type="citekey">wang-etal-2024-telechat</identifier>
<location>
<url>https://aclanthology.org/2024.sighan-1.2</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>10</start>
<end>20</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TeleChat: An Open-source Billingual Large Language Model
%A Wang, Zihan
%A Liuxz2@chinatelecom.cn, Liuxz2@chinatelecom.cn
%A Liusx14@chinatelecom.cn, Liusx14@chinatelecom.cn
%A Yao, Yitong
%A Huangyy121@chinatelecom.cn, Huangyy121@chinatelecom.cn
%A Mengxiang, Li
%A He, Zhongjiang
%A Liyx25@chinatelecom.cn, Liyx25@chinatelecom.cn
%A Pulw@chinatelecom.cn, Pulw@chinatelecom.cn
%A Xuhn@chinatelecom.cn, Xuhn@chinatelecom.cn
%A Wang, Chao
%A Song, Shuangyong
%Y Wong, Kam-Fai
%Y Zhang, Min
%Y Xu, Ruifeng
%Y Li, Jing
%Y Wei, Zhongyu
%Y Gui, Lin
%Y Liang, Bin
%Y Zhao, Runcong
%S Proceedings of the 10th SIGHAN Workshop on Chinese Language Processing (SIGHAN-10)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F wang-etal-2024-telechat
%X In this paper, we present TeleChat, a collection of large language models (LLMs) with parameters of 7 billion and 12 billion. TeleChat is initially pretrained on an extensive corpus containing a diverse collection of texts from both English and Chinese languages, encompassing trillions of tokens. Subsequently, the model undergoes fine-tuning to align with human preferences, following a detailed methodology that we describe. We evaluate the performance of TeleChat on various tasks, including general dialogue generation, language understanding, mathematics, reasoning, code generation, and knowledge-based question answering. Our findings indicate that TeleChat achieves state-of-the-art performance to other open-source models of similar size across a wide range of public benchmarks. To support future research and applications utilizing LLMs, we release the fine-tuned model checkpoints of TeleChat-7B and TeleChat-12B, along with code and a portion of our filtered high-quality pretraining data, to the public community.
%U https://aclanthology.org/2024.sighan-1.2
%P 10-20
Markdown (Informal)
[TeleChat: An Open-source Billingual Large Language Model](https://aclanthology.org/2024.sighan-1.2) (Wang et al., SIGHAN-WS 2024)
ACL
- Zihan Wang, Liuxz2@chinatelecom.cn Liuxz2@chinatelecom.cn, Liusx14@chinatelecom.cn Liusx14@chinatelecom.cn, Yitong Yao, Huangyy121@chinatelecom.cn Huangyy121@chinatelecom.cn, Li Mengxiang, Zhongjiang He, Liyx25@chinatelecom.cn Liyx25@chinatelecom.cn, Pulw@chinatelecom.cn Pulw@chinatelecom.cn, Xuhn@chinatelecom.cn Xuhn@chinatelecom.cn, Chao Wang, and Shuangyong Song. 2024. TeleChat: An Open-source Billingual Large Language Model. In Proceedings of the 10th SIGHAN Workshop on Chinese Language Processing (SIGHAN-10), pages 10–20, Bangkok, Thailand. Association for Computational Linguistics.