Axcxept × Alibaba Cloud — Real-time Analytics

Axcxept

Real-time Analytics

In the LLM landscape of Japan, there isn’t a dominant “go-to” LLM specifically for the Japanese speaker market. Axcxept wanted to pinpoint a base LLM that worked better with Japanese as a language, as well as incorporating nuanced cultural substance.

Reported impact

Business outcome

A fine-tuned implementation based on Qwen2.5, EZO x Qwen2.5 achieved accuracy that exceeded that of existing closed models in the Japanese MT Bench, the top Japanese language evaluation index in Japan. It also has the advantage of being lightweight and low latency, and is able to run at high speed on large-scale servers, typically found in many industries. The EZO x Qwen2.5 model outperforms GPT-4-Turbo across areas including coding, extraction, math, reasoning, roleplay, and writing with a total average score of 8.44 compared to the GPT score of 8.35.

Solution

Axcxept used Alibaba Cloud to address In the LLM landscape of Japan, there isn’t a dominant “go-to” LLM specifically for the Japanese speaker market. Axcxept wanted to pinpoint a base LLM that worked better with Japanese as a language, as well as incorporating nuanced cultural substance. Axcxept focuses on maximizing the power of AI and cloud computing. The invention of company name "Axcxept" underscores their determination to embrace the technological intersection of AI and cloud, and to transform to the changing times in a highly adaptable manner. Above all else, the company pursues safety and efficiency, and provides industry-leading diversified solutions and services. Qwen 2.0's impressive Japanese language processing capabilities attracted a lot of interest across social media. Following this, Qwen2.5 has improved Japanese language processing capabilities even further.

Solution architecture

1 components · 1 layer

Uncategorized
- Tongyi Qianwen (Qwen) The EZO series is implemented with fine tuning based on

Architecture clues

A fine-tuned implementation based on Qwen2.5, EZO x Qwen2.5 achieved accuracy that exceeded that of existing closed models in the Japanese MT Bench, the top Japanese language evaluation index in Japan
Following this, Qwen2.5 has improved Japanese language processing capabilities even further
It also has the advantage of being lightweight and low latency, and is able to run at high speed on large-scale servers, typically found in many industries
Qwen 2.0's impressive Japanese language processing capabilities attracted a lot of interest across social media
The EZO series is implemented with fine tuning based on Qwen2.5
The EZO x Qwen2.5 model outperforms GPT-4-Turbo across areas including coding, extraction, math, reasoning, roleplay, and writing with a total average score of 8.44 compared to the GPT score of 8.35

Evidence from the source

Axcxept wanted to pinpoint a base LLM that worked better with Japanese as a language, as well as incorporating nuanced cultural substance.

In the LLM landscape of Japan, there isn’t a dominant “go-to” LLM specifically for the Japanese speaker market.

The 32B and 72B models are equipped with technology incorporating Auto-CoT and Real-time Augmented Generation (RAG).

The EZO series is implemented with fine tuning based on Qwen2.5.

This allows for complex Japanese language support, as well as continuous updating.

Axcxept

Business outcome

Solution

Solution architecture

Architecture clues

Evidence from the source

How scores are calculated

Sources & provenance

Axcxept customer story

Date evidence

Similar use cases