Downloads · 30 days
241
5% of all-time downloads
lordjia/Qwen2-Cantonese-7B-Instruct
Qwen2-Cantonese-7B-Instruct is a text generation model from lordjia. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
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 a…
Downloads · 30 days
241
5% of all-time downloads
All-time downloads
4.7K
Public
Parameters
7.6B
19.7 GB on disk
Likes
4
Public
Click a slice to open those files.
.safetensors15.2 GB · 77%
From the Hugging Face model README
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。
A 4-bit quantized version of this model is also available: 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。
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:
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。
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 23.50 |
| IFEval (0-Shot) | 54.35 |
| BBH (3-Shot) | 32.45 |
| MATH Lvl 5 (4-Shot) | 8.76 |
| GPQA (0-shot) | 6.04 |
| MuSR (0-shot) | 7.81 |
| MMLU-PRO (5-shot) | 31.59 |