|
--- |
|
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 |
|
|
|
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. |
|
|
|
## Model Features |
|
|
|
- **Base Model**: Qwen2-7B-Instruct |
|
- **Fine-tuning Method**: LoRA instruction tuning |
|
- **Training Steps**: 4572 steps |
|
- **Primary Language**: Cantonese |
|
- **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 |
|
|
|
You can easily load and use this model with Hugging Face's Transformers library. Here is a simple example: |
|
|
|
```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 |
|
|
|
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). |
|
|
|
## Alternative Model Recommendation |
|
|
|
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. |
|
|
|
## License |
|
|
|
This model is licensed under the Apache 2.0 license. Please review the terms before use. |
|
|
|
## Contributors |
|
|
|
- LordJia |
|
|
|
## Acknowledgements |
|
|
|
Thanks to Hugging Face for providing the platform and tools, and to all the developers and researchers contributing to the open-source community. |
|
|
