Files
zeekay a30ff37468 Restore the Qwen names a blog rewrite erased
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.
2026-09-30 07:01:40 -07:00

13 lines
533 B
JSON

{
"title": "Example: Vertical Text Recognition",
"messages": [
{
"role": "User",
"content": "Read all texts in the image, output in lines.\n![image](https://qianwen-res.oss-accelerate-overseas.aliyuncs.com/Qwen2.5-VL/ocr_vertical.jpg)"
},
{
"role": "Qwen2.5-VL",
"content": "平安喜樂 \n八方來財 \n順風順水順財神 \n暴富 \n大吉 \n諸事皆順 \n福 \n時來運轉 \n發財 \n如意 \n有錢有勢有前程 \n好運來"
}
]
}