Commit
•
f3d098c
1
Parent(s):
b89d371
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
---
|
4 |
+
|
5 |
+
![Aquila_logo](./log.jpeg)
|
6 |
+
|
7 |
+
<h4 align="center">
|
8 |
+
<p>
|
9 |
+
<b>English</b> |
|
10 |
+
<a href="https://huggingface.co/BAAI/Aquila2-7B/blob/main/README_zh.md">简体中文</a> |
|
11 |
+
<p>
|
12 |
+
</h4>
|
13 |
+
|
14 |
+
|
15 |
+
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.
|
16 |
+
|
17 |
+
- 🌟 **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/Aquila-7B/resolve/main/BAAI%20Aquila%20Model%20License%20Agreement.pdf). Users can use it for commercial purposes as long as they meet the licensing restrictions.
|
18 |
+
|
19 |
+
- ✍️ **Possesses Chinese and English knowledge**. The Aquila series model is trained from scratch on a high-quality corpus of Chinese and English languages, with Chinese corpora accounting for about 40%, ensuring that the model accumulates native Chinese world knowledge during the pre-training phase, rather than translated knowledge.
|
20 |
+
|
21 |
+
- 👮♀️ **Complies with domestic data regulations**. The Chinese corpora of the Aquila series models come from Intelligence Source's accumulated Chinese datasets over the years, including Chinese internet data from over 10,000 sources (more than 99% of which are domestic sources), as well as high-quality Chinese literature and book data supported by authoritative domestic organizations. We will continue to accumulate high-quality and diverse datasets and incorporate them into the subsequent training of the Aquila base models.
|
22 |
+
|
23 |
+
- 🎯 **Continuous improvements and open sourcing**. We will continue to improve training data, optimize training methods, and enhance model performance, cultivate a flourishing "model tree" on a better base model foundation, and continuously update open-source versions.
|
24 |
+
|
25 |
+
The additional details of the Aquila model will be presented in the official technical report. Please stay tuned for updates on official channels.
|
26 |
+
|
27 |
+
|
28 |
+
|
29 |
+
|
30 |
+
## Quick Start Aquila-7B
|
31 |
+
|
32 |
+
### 1. Inference
|
33 |
+
|
34 |
+
```python
|
35 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
36 |
+
import torch
|
37 |
+
|
38 |
+
model_info = "BAAI/Aquila2-7B"
|
39 |
+
tokenizer = AutoTokenizer.from_pretrained(model_info, trust_remote_code=True)
|
40 |
+
model = AutoModelForCausalLM.from_pretrained(model_info, trust_remote_code=True)
|
41 |
+
model.eval()
|
42 |
+
model.to("cuda:0")
|
43 |
+
|
44 |
+
text = "汽车EDR是什么"
|
45 |
+
|
46 |
+
tokens = tokenizer.encode_plus(text)['input_ids'][:-1]
|
47 |
+
|
48 |
+
tokens = torch.tensor(tokens)[None,].to("cuda:0")
|
49 |
+
|
50 |
+
|
51 |
+
with torch.no_grad():
|
52 |
+
out = model.generate(tokens, do_sample=True, max_length=512, eos_token_id=100007)[0]
|
53 |
+
|
54 |
+
out = tokenizer.decode(out.cpu().numpy().tolist())
|
55 |
+
|
56 |
+
print(out)
|
57 |
+
```
|
58 |
+
|
59 |
+
|
60 |
+
## License
|
61 |
+
|
62 |
+
Aquila-7B and AquilaChat-33B open-source model is licensed under [ BAAI Aquila Model Licence Agreement](https://huggingface.co/BAAI/Aquila-7B/resolve/main/BAAI%20Aquila%20Model%20License%20Agreement.pdf)
|