Total runs:
6.0M
Run Growth:
1.3M
Growth Rate:
22.01%
BAAI / AquilaSQL-7B
Model's Last Updated: October 09 2023
Introduction of AquilaSQL-7B
Model Details of AquilaSQL-7B
English | 简体中文
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.
-
🌟 Supports open source commercial licenses . The source code of the Aquila series models is based on the Apache 2.0 agreement , while the model weight is based on the BAAI Aquila Model License Agreement . Users can use it for commercial purposes as long as they meet the licensing restrictions.
-
✍️ 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.
-
👮♀️ 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.
-
🎯 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.
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 , FlagAI's Zhihu account and FlagAI's official technical communication group .
| Model | Model Type | Description | Status | GPUs Used |
|---|---|---|---|---|
| AquilaSQL-7B | chat model | text2sql model, cotinue traind from the AquilaCode-base model, AquilaSQL achieved sota on the cspider leadboard | published | Nvidia-A100 |
We will continue to release improved versions of Aquila model as open source. ( https://huggingface.co/BAAI/AquilaSQL-7B/blob/main/change_log.log ).
Inference
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
device = torch.device("cuda")
model_info = "BAAI/AquilaSQL-7B"
tokenizer = AutoTokenizer.from_pretrained(model_info, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
model_info, trust_remote_code=True, torch_dtype=torch.float16, device_map='auto')
model.eval()
model.to(device)
torch.manual_seed(123)
text = "有多个数据库表，信息如下：\n表名为cars_data，包含的属性为cars_data.horsepower,cars_data.accelerate,cars_data.mpg,cars_data.id,cars_data.year;表名为continents，包含的属性为continents.contid,continents.continent;表名为countries，包含的属性为countries.continent,countries.countryname,countries.countryid;表名为model_list，包含的属性为model_list.model,model_list.maker,model_list.modelid，它们之间的关系为 countries.continent = continents.contid\n请为下面的问题编写sql查询语句：\n加速度比马力最大的汽车更大的汽车有多少辆？ "
def generate_prompt(input: str):
prompt = f"A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.###Human: {input}###Assistant:"
return prompt
stop_tokens = ["###", "[UNK]", "</s>","<|endoftext|>"]
with torch.no_grad():
_input = generate_prompt(text)
tokens = tokenizer.encode_plus(_input, None, max_length=None)['input_ids']
tokens = torch.tensor(tokens)[None,].to(device)
out = model.generate(tokens, do_sample=False, max_length=1024, eos_token_id=100007,max_new_tokens=512,
bad_words_ids=[[tokenizer.encode(token)[0] for token in stop_tokens]])[0]
out = tokenizer.decode(out.cpu().numpy().tolist())
print(out)
License
AquilaSQL-7B open-source model is licensed under BAAI Aquila Model Licence Agreement
Runs of BAAI AquilaSQL-7B on huggingface.co
15
Total runs
0
24-hour runs
1
3-day runs
4
7-day runs
9
30-day runs
More Information About AquilaSQL-7B huggingface.co Model
Url of AquilaSQL-7B
AquilaSQL-7B huggingface.co Url
Provider of AquilaSQL-7B huggingface.co
Other API from BAAI
Updated: February 22 2024
Total runs:
2.1M
Run Growth:
-2.4M
Growth Rate:
-114.86%
Total runs:
1.6M
Run Growth:
-268.0K
Growth Rate:
-16.69%
Total runs:
1.2M
Run Growth:
474.2K
Growth Rate:
40.50%
Total runs:
1.0M
Run Growth:
-41.8K
Growth Rate:
-4.05%
Total runs:
1.0M
Run Growth:
653.0K
Growth Rate:
64.13%
Total runs:
926.9K
Run Growth:
152.8K
Growth Rate:
17.17%
Total runs:
784.0K
Run Growth:
119.0K
Growth Rate:
15.18%
Total runs:
166.7K
Run Growth:
-19.2K
Growth Rate:
-11.50%
Total runs:
139.4K
Run Growth:
46.2K
Growth Rate:
33.17%
Total runs:
134.1K
Run Growth:
11.2K
Growth Rate:
8.36%
Total runs:
24.7K
Run Growth:
-1.7K
Growth Rate:
-7.58%
Total runs:
13.2K
Run Growth:
4.0K
Growth Rate:
30.16%
Total runs:
7.5K
Run Growth:
-923
Growth Rate:
-12.23%
Total runs:
7.4K
Run Growth:
-11.1K
Growth Rate:
-84.72%
Total runs:
6.4K
Run Growth:
-459
Growth Rate:
-7.17%
Total runs:
6.0K
Run Growth:
-3.2K
Growth Rate:
-49.29%
Total runs:
5.4K
Run Growth:
-1.3K
Growth Rate:
-24.73%
Total runs:
5.3K
Run Growth:
-1.2K
Growth Rate:
-23.23%
Total runs:
5.3K
Run Growth:
-1.2K
Growth Rate:
-22.97%
Total runs:
5.2K
Run Growth:
-2.8K
Growth Rate:
-54.34%
Total runs:
5.0K
Run Growth:
2.5K
Growth Rate:
48.72%
Total runs:
4.2K
Run Growth:
1.1K
Growth Rate:
26.24%
Total runs:
3.7K
Run Growth:
-875
Growth Rate:
-23.73%
Total runs:
3.6K
Run Growth:
-1.0K
Growth Rate:
-27.65%
Total runs:
2.8K
Run Growth:
196
Growth Rate:
7.14%
Total runs:
2.0K
Run Growth:
786
Growth Rate:
41.63%
Total runs:
1.3K
Run Growth:
1.0K
Growth Rate:
83.28%
Total runs:
1.1K
Run Growth:
25
Growth Rate:
86.21%
Total runs:
664
Run Growth:
0
Growth Rate:
0.00%
Total runs:
644
Run Growth:
0
Growth Rate:
0.00%
Total runs:
454
Run Growth:
-633
Growth Rate:
-29.46%
Total runs:
404
Run Growth:
71
Growth Rate:
17.57%
Total runs:
315
Run Growth:
-209
Growth Rate:
-66.35%
Total runs:
202
Run Growth:
38
Growth Rate:
19.19%
Total runs:
134
Run Growth:
-198
Growth Rate:
-147.76%
Total runs:
101
Run Growth:
75
Growth Rate:
74.26%
Total runs:
61
Run Growth:
-95
Growth Rate:
-150.79%
Total runs:
59
Run Growth:
11
Growth Rate:
17.74%
Total runs:
39
Run Growth:
3
Growth Rate:
100.00%
Total runs:
31
Run Growth:
-9.1K
Growth Rate:
-29351.61%
Total runs:
28
Run Growth:
-440
Growth Rate:
-427.18%
Total runs:
26
Run Growth:
3
Growth Rate:
100.00%
Total runs:
24
Run Growth:
1
Growth Rate:
100.00%
Total runs:
18
Run Growth:
-18
Growth Rate:
-100.00%