mirror of
https://github.com/zenlm/zen-blog.git
synced 2026-11-03 14:11:45 +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.
13 lines
1.0 KiB
JSON
13 lines
1.0 KiB
JSON
{
|
|
"title": "Example: Information Extraction from Videos",
|
|
"messages": [
|
|
{
|
|
"role": "User",
|
|
"content": "Watch the video and list the paper titles in a table.\n{{<video src=\"https://qianwen-res.oss-accelerate-overseas.aliyuncs.com/Qwen2.5-VL/video_ocr.mp4\" controls=\"true\" muted=\"true\" width=\"50%\" >}}"
|
|
},
|
|
{
|
|
"role": "Qwen2.5-VL",
|
|
"content": "Here is a table listing the paper titles from the video:\n\n| Paper Title |\n|-------------|\n| A New Sequential Prediction Framework with Spatial-temporal Embedding |\n| NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation |\n| Deep Unified Representation for Heterogeneous Recommendation |\n| OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework |\n| KoMen: Domain Knowledge Guided Interaction Recommendation for Emerging Scenarios Yiqing Xie |\n| Vision-Language Pre-Training for Boosting Scene Text Detectors |"
|
|
}
|
|
]
|
|
} |