Commit
·
f7804a8
1
Parent(s):
0f29961
fix readme
Browse files
README.md
CHANGED
|
@@ -5,7 +5,6 @@ license: other
|
|
| 5 |
|
| 6 |

|
| 7 |
|
| 8 |
-
|
| 9 |
<h4 align="center">
|
| 10 |
<p>
|
| 11 |
<b>English</b> |
|
|
@@ -13,6 +12,7 @@ license: other
|
|
| 13 |
</p>
|
| 14 |
</h4>
|
| 15 |
|
|
|
|
| 16 |
Aquila Language Model is the first open source language model that supports both Chinese and English knowledge, commercial license agreements, and compliance with domestic data regulations.
|
| 17 |
|
| 18 |
- 🌟 **Supports open source commercial licenses**. The source code of the Aquila series models is based on the [Apache 2.0 agreement](https://www.apache.org/licenses/LICENSE-2.0), while the model weight is based on the [BAAI Aquila Model License Agreement](https://huggingface.co/BAAI/AquilaChat-7B/resolve/main/BAAI%20Aquila%20Model%20License%20Agreement.pdf). Users can use it for commercial purposes as long as they meet the licensing restrictions.
|
|
@@ -25,22 +25,18 @@ Aquila Language Model is the first open source language model that supports both
|
|
| 25 |
|
| 26 |
The additional details of the Aquila model will be presented in the official technical report. Please stay tuned for updates on official channels, including the [FlagAI GitHub repository](https://github.com/FlagAI-Open/FlagAI/), [FlagAI's Zhihu account](https://www.zhihu.com/people/95-22-20-18) and [FlagAI's official technical communication group](https://github.com/FlagAI-Open/FlagAI/blob/master/wechat-qrcode.jpg).
|
| 27 |
|
|
|
|
|
|
|
|
|
|
| 28 |
|
| 29 |
|
| 30 |
|
| 31 |
-
| Model | Model Type | Description | Status | GPUs Used |
|
| 32 |
-
| :----------------- | :----------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | :--------------| :----------- |
|
| 33 |
-
|
| 34 |
-
| AquilaSQL-7B |chat model | text2sql model, cotinue traind from the AquilaCode-base model| AquilaSQL achieved sota on the cspider leadboard | published | Nvidia-A100 |
|
| 35 |
-
|
| 36 |
We will continue to release improved versions of Aquila model as open source.
|
| 37 |
(https://huggingface.co/BAAI/AquilaSQL-7B/blob/main/change_log.log).
|
| 38 |
|
| 39 |
<!-- </table> -->
|
| 40 |
|
| 41 |
-
##
|
| 42 |
-
|
| 43 |
-
### 1. Inference
|
| 44 |
|
| 45 |
```python
|
| 46 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
|
|
|
| 5 |
|
| 6 |

|
| 7 |
|
|
|
|
| 8 |
<h4 align="center">
|
| 9 |
<p>
|
| 10 |
<b>English</b> |
|
|
|
|
| 12 |
</p>
|
| 13 |
</h4>
|
| 14 |
|
| 15 |
+
|
| 16 |
Aquila Language Model is the first open source language model that supports both Chinese and English knowledge, commercial license agreements, and compliance with domestic data regulations.
|
| 17 |
|
| 18 |
- 🌟 **Supports open source commercial licenses**. The source code of the Aquila series models is based on the [Apache 2.0 agreement](https://www.apache.org/licenses/LICENSE-2.0), while the model weight is based on the [BAAI Aquila Model License Agreement](https://huggingface.co/BAAI/AquilaChat-7B/resolve/main/BAAI%20Aquila%20Model%20License%20Agreement.pdf). Users can use it for commercial purposes as long as they meet the licensing restrictions.
|
|
|
|
| 25 |
|
| 26 |
The additional details of the Aquila model will be presented in the official technical report. Please stay tuned for updates on official channels, including the [FlagAI GitHub repository](https://github.com/FlagAI-Open/FlagAI/), [FlagAI's Zhihu account](https://www.zhihu.com/people/95-22-20-18) and [FlagAI's official technical communication group](https://github.com/FlagAI-Open/FlagAI/blob/master/wechat-qrcode.jpg).
|
| 27 |
|
| 28 |
+
| Model | Model Type | Description | Status | GPUs Used |
|
| 29 |
+
| ------------ | ---------- | ------------------------------------------------------------ | --------- | ----------- |
|
| 30 |
+
| AquilaSQL-7B | chat model | text2sql model, cotinue traind from the AquilaCode-base model, AquilaSQL achieved sota on the cspider leadboard | published | Nvidia-A100 |
|
| 31 |
|
| 32 |
|
| 33 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
We will continue to release improved versions of Aquila model as open source.
|
| 35 |
(https://huggingface.co/BAAI/AquilaSQL-7B/blob/main/change_log.log).
|
| 36 |
|
| 37 |
<!-- </table> -->
|
| 38 |
|
| 39 |
+
## Inference
|
|
|
|
|
|
|
| 40 |
|
| 41 |
```python
|
| 42 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|