---
license: apache-2.0
datasets:
- jed351/cantonese-wikipedia
- raptorkwok/cantonese-traditional-chinese-parallel-corpus
language:
- zh
- en
pipeline_tag: text-generation
tags:
- Cantonese
- Qwen2
- chat
---

# Qwen2-Cantonese-7B-Instruct

## Model Overview / 模型概述

Qwen2-Cantonese-7B-Instruct is a Cantonese language model based on Qwen2-7B-Instruct, fine-tuned using LoRA. It aims to enhance Cantonese text generation and comprehension capabilities, supporting various tasks such as dialogue generation, text summarization, and question-answering.

Qwen2-Cantonese-7B-Instruct係基於Qwen2-7B-Instruct嘅粵語語言模型，使用LoRA進行微調。 它旨在提高粵語文本的生成和理解能力，支持各種任務，如對話生成、文本摘要和問答。

## Model Features / 模型特性

- **Base Model**: Qwen2-7B-Instruct
- **Fine-tuning Method**: LoRA instruction tuning
- **Training Steps**: 4572 steps
- **Primary Language**: Cantonese / 粵語
- **Datasets**:
  - [jed351/cantonese-wikipedia](https://huggingface.co/datasets/jed351/cantonese-wikipedia)
  - [raptorkwok/cantonese-traditional-chinese-parallel-corpus](https://huggingface.co/datasets/raptorkwok/cantonese-traditional-chinese-parallel-corpus)
- **Training Tools**: [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory)

## Usage / 用法

You can easily load and use this model with Hugging Face's Transformers library. Here is a simple example:

你可以輕鬆地將此模型與Hugging Face嘅Transformers庫一起使用。 下面係一個簡單嘅示例：

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("lordjia/Qwen2-Cantonese-7B-Instruct")
model = AutoModelForCausalLM.from_pretrained("lordjia/Qwen2-Cantonese-7B-Instruct")

input_text = "唔該你用廣東話講下你係邊個。"
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## Quantized Version / 量化版本

A 4-bit quantized version of this model is also available: [qwen2-cantonese-7b-instruct-q4_0.gguf](https://huggingface.co/lordjia/Qwen2-Cantonese-7B-Instruct/blob/main/qwen2-cantonese-7b-instruct-q4_0.gguf).

此外，仲提供此模型嘅4位量化版本：[qwen2-cantonese-7b-instruct-q4_0.gguf](https://huggingface.co/lordjia/Qwen2-Cantonese-7B-Instruct/blob/main/qwen2-cantonese-7b-instruct-q4_0.gguf)。

## Alternative Model Recommendation / 備選模型舉薦

For an alternative, consider [Llama-3-Cantonese-8B-Instruct](https://huggingface.co/lordjia/Llama-3-Cantonese-8B-Instruct), also fine-tuned by LordJia and based on Meta-Llama-3-8B-Instruct.

對於替代方案，請考慮[Llama-3-Cantonese-8B-Instruct](https://huggingface.co/lordjia/Llama-3-Cantonese-8B-Instruct)，同樣由LordJia微調並基於Meta-Llama-3-8B-Instruct。

## License / 許可證

This model is licensed under the Apache 2.0 license. Please review the terms before use.

此模型喺Apache 2.0許可證下獲得許可。 請在使用前仔細閱讀呢啲條款。

## Contributors / 貢獻

- LordJia [https://ai.chao.cool](https://ai.chao.cool/)