shibing624 / llama-13b-belle-zh-lora

huggingface.co
Total runs: 0
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Model's Last Updated: April 14 2023

Introduction of llama-13b-belle-zh-lora

Model Details of llama-13b-belle-zh-lora

Chinese QA LoRA Model

llama中文问答LoRA模型

llama-13B-belle-zh-lora evaluate test data:

The overall performance of llama-13B-belle-zh-lora on QA test :

input_text predict
用一句话描述地球为什么是独一无二的\n答: 地球是独一无二的,因为它是我们的家园,它是我们的生命的基础,它是我们的星球。

在中文开放测试集中的表现优异,继承了两方面的优势:1)微调的底座是llama-13B模型,中文的表现优于LLAMA,2)微调使用的是高质量100万条中文ChatGPT指令Belle数据集,微调后的模型对话效果优于原始llama-13B。

Usage

本项目开源在textgen项目: textgen ,可支持llama模型,通过如下命令调用:

Install package:

pip install -U textgen
from textgen import LlamaModel
model = LlamaModel("llama", "decapoda-research/llama-13b-hf", lora_name="shibing624/llama-13b-belle-zh-lora")
r = model.predict(["用一句话描述地球为什么是独一无二的\n答:"])
print(r) # ['地球是独一无二的,因为它是我们的家园,它是我们的生命的基础,它是我们的星球。']

模型文件组成:

llama-13b-belle-zh-lora
    ├── adapter_config.json
    └── adapter_model.bin
训练数据集
  1. 50万条中文ChatGPT指令Belle数据集: BelleGroup/train_0.5M_CN
  2. 100万条中文ChatGPT指令Belle数据集: BelleGroup/train_1M_CN
  3. 5万条英文ChatGPT指令Alpaca数据集: 50k English Stanford Alpaca dataset
  4. 2万条中文ChatGPT指令Alpaca数据集: shibing624/alpaca-zh
  5. 69万条中文指令Guanaco数据集(Belle50万条+Guanaco19万条): Chinese-Vicuna/guanaco_belle_merge_v1.0

如果需要训练llama模型,请参考 https://github.com/shibing624/textgen

Citation
@software{textgen,
  author = {Xu Ming},
  title = {textgen: Implementation of language model finetune},
  year = {2021},
  url = {https://github.com/shibing624/textgen},
}

Runs of shibing624 llama-13b-belle-zh-lora on huggingface.co

0
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs

More Information About llama-13b-belle-zh-lora huggingface.co Model

More llama-13b-belle-zh-lora license Visit here:

https://choosealicense.com/licenses/apache-2.0

llama-13b-belle-zh-lora huggingface.co

llama-13b-belle-zh-lora huggingface.co is an AI model on huggingface.co that provides llama-13b-belle-zh-lora's model effect (), which can be used instantly with this shibing624 llama-13b-belle-zh-lora model. huggingface.co supports a free trial of the llama-13b-belle-zh-lora model, and also provides paid use of the llama-13b-belle-zh-lora. Support call llama-13b-belle-zh-lora model through api, including Node.js, Python, http.

llama-13b-belle-zh-lora huggingface.co Url

https://huggingface.co/shibing624/llama-13b-belle-zh-lora

shibing624 llama-13b-belle-zh-lora online free

llama-13b-belle-zh-lora huggingface.co is an online trial and call api platform, which integrates llama-13b-belle-zh-lora's modeling effects, including api services, and provides a free online trial of llama-13b-belle-zh-lora, you can try llama-13b-belle-zh-lora online for free by clicking the link below.

shibing624 llama-13b-belle-zh-lora online free url in huggingface.co:

https://huggingface.co/shibing624/llama-13b-belle-zh-lora

llama-13b-belle-zh-lora install

llama-13b-belle-zh-lora is an open source model from GitHub that offers a free installation service, and any user can find llama-13b-belle-zh-lora on GitHub to install. At the same time, huggingface.co provides the effect of llama-13b-belle-zh-lora install, users can directly use llama-13b-belle-zh-lora installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

llama-13b-belle-zh-lora install url in huggingface.co:

https://huggingface.co/shibing624/llama-13b-belle-zh-lora

Url of llama-13b-belle-zh-lora

llama-13b-belle-zh-lora huggingface.co Url

Provider of llama-13b-belle-zh-lora huggingface.co

shibing624
ORGANIZATIONS

Other API from shibing624