Instructions to use AXERA-TECH/LocateAnything-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AXERA-TECH/LocateAnything-3B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-object-detection", model="AXERA-TECH/LocateAnything-3B")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("AXERA-TECH/LocateAnything-3B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -45,34 +45,6 @@ For those who are interested in model conversion, you can try to export axmodel
|
|
| 45 |
|
| 46 |
The DDR capacity refers to the CMM memory that needs to be consumed. Ensure that the CMM memory allocation on the development board is greater than this value.
|
| 47 |
|
| 48 |
-
## How to use
|
| 49 |
-
|
| 50 |
-
## 安装 axllm
|
| 51 |
-
方式一:克隆仓库后执行安装脚本:
|
| 52 |
-
|
| 53 |
-
```shell
|
| 54 |
-
git clone -b axllm https://github.com/AXERA-TECH/ax-llm.git
|
| 55 |
-
cd ax-llm
|
| 56 |
-
./install.sh
|
| 57 |
-
```
|
| 58 |
-
|
| 59 |
-
方式二:一行命令安装(默认分支 `axllm`):
|
| 60 |
-
|
| 61 |
-
```shell
|
| 62 |
-
curl -fsSL https://raw.githubusercontent.com/AXERA-TECH/ax-llm/axllm/install.sh | bash
|
| 63 |
-
```
|
| 64 |
-
|
| 65 |
-
方式三:下载Github Actions CI 导出的可执行程序(适合没有编译环境的用户):
|
| 66 |
-
|
| 67 |
-
如果没有编译环境,请到:
|
| 68 |
-
`https://github.com/AXERA-TECH/ax-llm/actions?query=branch%3Aaxllm`
|
| 69 |
-
下载 **最新 CI 导出的可执行程序**(`axllm`),然后:
|
| 70 |
-
|
| 71 |
-
```shell
|
| 72 |
-
chmod +x axllm
|
| 73 |
-
sudo mv axllm /usr/bin/axllm
|
| 74 |
-
```
|
| 75 |
-
|
| 76 |
## 模型下载(Hugging Face)
|
| 77 |
先创建模型目录并进入,然后下载到该目录:
|
| 78 |
|
|
|
|
| 45 |
|
| 46 |
The DDR capacity refers to the CMM memory that needs to be consumed. Ensure that the CMM memory allocation on the development board is greater than this value.
|
| 47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
## 模型下载(Hugging Face)
|
| 49 |
先创建模型目录并进入,然后下载到该目录:
|
| 50 |
|