mirror of
https://github.com/zenlm/zen-blog.git
synced 2026-11-02 17:28:53 +00:00
zeekay
a30ff37468
b3b6eb0 ran a find-and-replace over the posts forked from the QwenLM
blog that turned "Qwen2" and "Qwen2.5" into "zen": Qwen2-57B-A14B read
as zen7B-A14B, Qwen2-72B as zen-72B, Qwen2AudioForConditionalGeneration
as a class that does not exist, and links such as
github.com/QwenLM/Qwen2 and the qianwen-res image paths pointed at
nothing. Every token is put back from the original post, aligned
against the rewritten one: 536 lines across 29 posts, and 116 of the
example files under public/cases.
These 44 posts are about another lab's releases and now say so with
"upstream: true" in their frontmatter. Two Zen posts lose the
base-model names they carried, and the Zen 3 post stops calling itself
the next generation.
75 lines
2.7 KiB
Plaintext
75 lines
2.7 KiB
Plaintext
---
|
|
title: "Notes on Qwen-Max-0428"
|
|
date: "2024-05-11"
|
|
description: "Previously, we opensourced a series of Qwen1.5 model ranging from 0.5 to 110 billion parameters. Now, we release a larger model, Qwen-Max-0428. Qwen-Max-0428 is an instruction-tuned model for chat service. Very recently, it is available via [Chatbot Arena](https://chat.lmsys.org/) and it has now bec"
|
|
upstream: true
|
|
---
|
|
|
|
|
|
<LinkButton href="https://dashscope.aliyun.com" label="API" external />
|
|
<LinkButton href="https://huggingface.co/spaces/Qwen/Qwen-Max-0428" label="DEMO" external />
|
|
<LinkButton href="https://discord.gg/yPEP2vHTu4" label="DISCORD" external />
|
|
|
|
Previously, we opensourced a series of Qwen1.5 model ranging from 0.5 to 110 billion parameters. Now, we release a larger model, Qwen-Max-0428. Qwen-Max-0428 is an instruction-tuned model for chat service. Very recently, it is available via [Chatbot Arena](https://chat.lmsys.org/) and it has now become the top-10 in the leaderboard. Furthermore, our evaluation of MT-Bench also demonstrates that the new model outperforms our previous largest model Qwen1.5-110B-Chat.
|
|
|
|
<Figure src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/arena_leaderboard.jpg#center" width="100%" />
|
|
|
|
<table>
|
|
<tr>
|
|
<th rowspan="1">Models</th>
|
|
<th colspan="1">MT-Bench</th>
|
|
<th colspan="1">Arena</th>
|
|
</tr>
|
|
<tr>
|
|
<td>Qwen1.5-110B-Chat</td>
|
|
<td>8.88</td>
|
|
<td>1172</td>
|
|
</tr>
|
|
<tr>
|
|
<td>Qwen-Max-0428</td>
|
|
<td>8.96</td>
|
|
<td>1186</td>
|
|
</tr>
|
|
</table>
|
|
|
|
We provide a demo of chat service of Qwen-Max-0428 ([link](https://huggingface.co/spaces/Qwen/Qwen-Max-0428)) in Hugging Face Spaces:
|
|
|
|
<iframe
|
|
src="https://qwen-qwen-max-0428.hf.space"
|
|
frameborder="0"
|
|
width="850"
|
|
height="1000"
|
|
></iframe>
|
|
|
|
It is also accessible through the official DashScope API ([link](https://dashscope.aliyun.com)). Additionally, now the DashScope API is compatible with the OpenAI API format. Below is an example of usage:
|
|
|
|
```python
|
|
from openai import OpenAI
|
|
|
|
client = OpenAI(
|
|
api_key="$your-dashscope-api-key",
|
|
base_url="https://dashscope.aliyuncs.com/compatible-mode/v1"
|
|
)
|
|
|
|
completion = client.chat.completions.create(
|
|
model="qwen-max",
|
|
messages=[{'role': 'system', 'content': 'You are a helpful assistant.'},
|
|
{'role': 'user', 'content': 'Tell me something about large language models.'}]
|
|
)
|
|
print(completion.choices[0].message)
|
|
```
|
|
|
|
This model is available in our web service and APP ([link](https://tongyi.aliyun.com/qianwen/), only accessible in mainland China). Enjoy!
|
|
|
|
|
|
# Citation
|
|
|
|
```
|
|
@misc{qwen1.5,
|
|
title = {Introducing Qwen1.5},
|
|
url = {https://qwenlm.github.io/blog/qwen1.5/},
|
|
author = {Qwen Team},
|
|
month = {February},
|
|
year = {2024}
|
|
}
|
|
``` |