Aquila Models by Beijing Academy of Artificial Intelligence (BAAI)
About
The Aquila family of large language models (LLMs), developed by the Beijing Academy of Artificial Intelligence (BAAI), includes open-source models that cater to both Chinese and English language requirements 35. These models adhere to Chinese domestic data regulations, offering commercial licenses that are crucial for wide adoption 35. The Aquila series features base models such as Aquila-7B and Aquila-33B, along with specialized versions like AquilaChat-7B for dialogue and AquilaCode-7B for coding tasks 35. With a significant focus on Chinese data, the models are trained to ensure native-level comprehension. BAAI also integrates advanced architectures from GPT-3 and LLaMA, employing efficient operators and a redesigned bilingual tokenizer for enhanced performance 1. The AquilaChat models excel in text dialogue and versatile language generation, while the AquilaCode models are recognized as leading open-source solutions for code generation in Chinese and English 5.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Aquila Chat 33B | Use when the workload needs 33B parameters. | 2023-10 | 33B parameters | Current |
| Aquila Chat 7B | Use when the workload needs 7B parameters. | 2023-10 | 7B parameters | Current |
| Aquila 33B | Use when the workload needs 33B parameters. | 2023-10 | 33B parameters | Current |
| Aquila 7B | Use when the workload needs 7B parameters. | 2023-10 | 7B parameters | Current |
Release Timeline
1 release groupSpecifications(4 models)
| Model | Released | Parameters |
|---|---|---|
| Aquila Chat 33B | 2023-10 | 33B |
| Aquila Chat 7B | 2023-10 | 7B |
| Aquila 33B | 2023-10 | 33B |
| Aquila 7B | 2023-10 | 7B |
Frequently Asked Questions
- What is Aquila used for?
- Aquila is used for coding. The family description and listed model capabilities point to those workloads as the best fit.
- How does Aquila compare to BGE?
- Aquila by Beijing Academy of Artificial Intelligence (BAAI) is strongest where you need coding, while BGE by Beijing Academy of Artificial Intelligence (BAAI) is the closest related family to check for embedding. Aquila has 4 listed variants, while BGE reaches up to 8k context, so compare the specs and pricing tables before choosing a production model.
- Which Aquila model should I use?
- If price is the main constraint, use the pricing table first because Aquila does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate Aquila Chat 33B.
