58 lines
2.5 KiB
Markdown
58 lines
2.5 KiB
Markdown
---
|
||
license: llama3.1
|
||
datasets:
|
||
- jed351/cantonese-wikipedia
|
||
- lordjia/Cantonese_English_Translation
|
||
language:
|
||
- en
|
||
- zh
|
||
pipeline_tag: text-generation
|
||
tags:
|
||
- Cantonese
|
||
- chat
|
||
- Llama3.1
|
||
---
|
||
|
||
# Llama-3.1-Cantonese-8B-Instruct
|
||
|
||
## Model Overview / 模型概述
|
||
|
||
Llama-3.1-Cantonese-8B-Instruct is a Cantonese language model based on Meta-Llama-3.1-8B-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.
|
||
|
||
Llama-3.1-Cantonese-8B-Instruct係基於Meta-Llama-3.1-8B-Struct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**: Meta-Llama-3.1-8B-Instruct
|
||
- **Fine-tuning Method**: LoRA instruction tuning
|
||
- **Training Steps**: 4497 steps
|
||
- **Primary Language**: Cantonese / 粵語
|
||
- **Datasets**:
|
||
- [jed351/cantonese-wikipedia](https://huggingface.co/datasets/jed351/cantonese-wikipedia)
|
||
- [lordjia/Cantonese_English_Translation](https://huggingface.co/datasets/lordjia/Cantonese_English_Translation)
|
||
- **Training Tools**: [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory)
|
||
|
||
## Quantized Version / 量化版本
|
||
|
||
A 4-bit quantized version of this model is also available: [llama3.1-cantonese-8b-instruct-q4_0.gguf](https://huggingface.co/lordjia/Llama-3.1-Cantonese-8B-Instruct/blob/main/llama3.1-cantonese-8b-instruct-q4_0.gguf).
|
||
|
||
此模型的4位量化版本也可用：[llama3.1-cantonese-8b-instruct-q4_0.gguf](https://huggingface.co/lordjia/Llama-3.1-Cantonese-8B-Instruct/blob/main/llama3.1-cantonese-8b-instruct-q4_0.gguf)。
|
||
|
||
## Alternative Model Recommendations / 備選模型舉薦
|
||
|
||
For alternatives, consider the following models, both fine-tuned by LordJia on Cantonese language tasks:
|
||
|
||
揾其他嘅話，可以諗下呢啲模型，全部都係LordJia用廣東話嘅工作調教好嘅：
|
||
|
||
1. [Qwen2-Cantonese-7B-Instruct](https://huggingface.co/lordjia/Qwen2-Cantonese-7B-Instruct) based on Qwen2-7B-Instruct.
|
||
2. [Llama-3-Cantonese-8B-Instruct](https://huggingface.co/lordjia/Llama-3-Cantonese-8B-Instruct) based on Meta-Llama-3-8B-Instruct.
|
||
|
||
## License / 許可證
|
||
|
||
This model is licensed under the Llama 3.1 Community License. Please review the terms before use.
|
||
|
||
此模型根據Llama 3.1社區許可證獲得許可。 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/) |