Instructions to use DataCanvas/Alaya-7B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DataCanvas/Alaya-7B-Base with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="DataCanvas/Alaya-7B-Base", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DataCanvas/Alaya-7B-Base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("DataCanvas/Alaya-7B-Base", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DataCanvas/Alaya-7B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DataCanvas/Alaya-7B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DataCanvas/Alaya-7B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DataCanvas/Alaya-7B-Base

SGLang

How to use DataCanvas/Alaya-7B-Base with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "DataCanvas/Alaya-7B-Base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DataCanvas/Alaya-7B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "DataCanvas/Alaya-7B-Base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DataCanvas/Alaya-7B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DataCanvas/Alaya-7B-Base with Docker Model Runner:
```
docker model run hf.co/DataCanvas/Alaya-7B-Base
```

九章元识 | DataCanvas Alaya

GitHub: https://github.com/DataCanvasIO/Alaya

九章云极DataCanvas重磅发布的元识大模型Alaya，在自主整理的高品质多语言数据集上训练了1.5T+ tokens。

首先在Hugging Face开源了7B-Base和7B-Chat版本，模型表现业内领先，知识丰富且富有时效性，最新数据覆盖2023年10月的内容。Alaya-7B-Chat具备多轮对话、自我认知和偏见拒答的能力，能够完成知识问答、代码编写、信息提取、阅读理解、创意写作等多项语言任务。

预训练参数

训练Alaya的过程中，使用的超参如下：

Hidden Dimension	4096
Number of Attention Heads	32
Number of Layers	32
Vocabulary Size	60160
Optimizer	Decoupled AdamW (beta=0.9, 0.95; epsilon = 1.0e-8)
Max Learning Rate	1.2e-4
Min Learning Rate	1.2e-5
Scheduler	Cosine Decay with Warmup
Weight Decay	1.0e-5
Gradient Clip Norm	0.3

声明

Alaya训练过程中已经采取多种措施进行数据的筛选与过滤，尽可能保证数据的合法合规，但由于神经网络的黑盒本质，即使训练数据相对干净，模型还是可能生成一些错误的、不可预见的或难以干预的回答。请谨慎使用！

请注意：

请勿使用Alaya进行任何违反法律法规或是危害国家安全的活动
请勿恶意引导Alaya生成不合适的回答
请勿使用Alaya侵犯他人或团体的权益
Alaya生成的文本不代表训练数据一定包含该信息，且不代表九章云极的立场

对于使用模型而导致的任何问题，九章云极将不承担任何责任。

联系我们

如果您在使用的过程中发现任何问题，想要提供意见或建议，欢迎联系：sophia@zetyun.com。

协议

Alaya使用Apache 2.0 Lisense，开放模型权重，允许商业用途。如果您的项目引用了我们的Alaya，请标明出处，可以使用以下citation：

@misc{datacanvas2023alaya,
    author = {DataCanvas Ltd.},
    title = {alaya},
    year = {2023},
    howpublished = {\url{https://github.com/DataCanvasIO/Alaya}},
}

Downloads last month: 15