Breeze-7B Technical Report

Autor: Hsu, Chan-Jan, Liu, Chang-Le, Liao, Feng-Ting, Hsu, Po-Chun, Chen, Yi-Chang, Shiu, Da-Shan
Rok vydání: 2024
Předmět:
Druh dokumentu: Working Paper
Popis: Breeze-7B is an open-source language model based on Mistral-7B, designed to address the need for improved language comprehension and chatbot-oriented capabilities in Traditional Chinese. This technical report provides an overview of the additional pretraining, finetuning, and evaluation stages for the Breeze-7B model. The Breeze-7B family of base and chat models exhibits good performance on language comprehension and chatbot-oriented tasks, reaching the top in several benchmarks among models comparable in its complexity class.
Databáze: arXiv