kennylam's picture
Add credits
70a37fa
metadata
pipeline_tag: text-generation
license: apache-2.0
language:
  - zh
  - en
datasets:
  - hon9kon9ize/yue-alpaca
  - indiejoseph/wikipedia-translate-zhhk-zhcn
  - indiejoseph/wikipedia-zh-yue-summaries
  - indiejoseph/wikipedia-zh-yue-qa
tags:
  - cantonese
  - yue
  - hong kong
  - 香港
  - 廣東話
  - 粵語

Model Card for Breeze-7B-Cantonese-v0.1

Breeze-7B is a language model family that builds on top of Mistral-7B, specifically intended for Traditional Chinese use. Credit to MediaTek-Research.
Breeze-7B係一個以Mistral-7B作為基礎,為正體中文而造嘅模型系列,由MediaTek-Research製作.

[Breeze-7B-Cantonese] derives from the base model Breeze-7B-Base, with finetuning by datasets from hon9kon9ize, making the resulting model to be able to chat with Cantonese.
[Breeze-7B-Cantonese] 係由基座模型 Breeze-7B-Base 衍生出黎,用hon9kon9ize 整嘅數據集微調, 令到呢個模型可以講廣東話。

I selected the [Breeze-7B-Base] model due to its extensive vocabulary coverage tailored for Traditional Chinese. Its language style aligns closely with the nuances of Hong Kong discourse, making it a suitable choice for this project.
我揀[Breeze-7B-Base]做基座模型係因為佢有正體中文嘅擴增詞表, 而且佢嘅語言根基同香港比較相似, 所以佢似乎比較適合呢個項目。

The axolotl config file axolotl-config.yml is shared for open-source purposes, allowing everyone to utilize it for training on their own.
為咗人人都可以自己訓練模型,我放埋個axolotl設定檔 axolotl-config.yml出嚟當開放源始碼。

Thanks for the great datasets from hon9kon9ize and indiejoseph, this project owes its existence to their invaluable contributions.
多得hon9kon9izeindiejoseph 放出嚟嘅數據集, 先至有呢個項目出現。