mirror of
https://github.com/zenlm/zen-blog.git
synced 2026-11-03 14:11:45 +00:00
27 lines
16 KiB
Plaintext
27 lines
16 KiB
Plaintext
1:"$Sreact.fragment"
|
||
2:I[106,["/_next/static/chunks/59d0ad1b64f8544e.js"],"RootProvider"]
|
||
3:I[53113,["/_next/static/chunks/4d80e004cf4896dd.js","/_next/static/chunks/350ee4303b732916.js"],"default"]
|
||
4:I[73211,["/_next/static/chunks/4d80e004cf4896dd.js","/_next/static/chunks/350ee4303b732916.js"],"default"]
|
||
5:I[10086,["/_next/static/chunks/59d0ad1b64f8544e.js","/_next/static/chunks/8de849ca74fc071f.js","/_next/static/chunks/e62b91212ee7f8ff.js","/_next/static/chunks/f19fe44237e54646.js","/_next/static/chunks/cb0a883bafeb6805.js"],""]
|
||
7:I[89923,["/_next/static/chunks/4d80e004cf4896dd.js","/_next/static/chunks/350ee4303b732916.js"],"OutletBoundary"]
|
||
8:"$Sreact.suspense"
|
||
a:I[89923,["/_next/static/chunks/4d80e004cf4896dd.js","/_next/static/chunks/350ee4303b732916.js"],"ViewportBoundary"]
|
||
c:I[89923,["/_next/static/chunks/4d80e004cf4896dd.js","/_next/static/chunks/350ee4303b732916.js"],"MetadataBoundary"]
|
||
e:I[6998,["/_next/static/chunks/4d80e004cf4896dd.js","/_next/static/chunks/350ee4303b732916.js"],"default"]
|
||
:HL["/_next/static/chunks/f2332aac77592f9d.css","style"]
|
||
0:{"P":null,"b":"i-dnJM_MIpJSOCQWNJVMq","c":["","blog","qwen2.5-omni"],"q":"","i":false,"f":[[["",{"children":["blog",{"children":[["slug","qwen2.5-omni","d"],{"children":["__PAGE__",{}]}]}]},"$undefined","$undefined",true],[["$","$1","c",{"children":[[["$","link","0",{"rel":"stylesheet","href":"/_next/static/chunks/f2332aac77592f9d.css","precedence":"next","crossOrigin":"$undefined","nonce":"$undefined"}],["$","script","script-0",{"src":"/_next/static/chunks/59d0ad1b64f8544e.js","async":true,"nonce":"$undefined"}]],["$","html",null,{"lang":"en","className":"dark","suppressHydrationWarning":true,"children":["$","body",null,{"className":"antialiased","children":["$","$L2",null,{"children":["$","$L3",null,{"parallelRouterKey":"children","error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L4",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","main",null,{"className":"flex min-h-screen flex-col items-center justify-center px-4 text-center","children":[["$","div",null,{"className":"mb-8 opacity-20","children":["$","svg",null,{"width":"120","height":"120","viewBox":"0 0 120 120","fill":"none","aria-hidden":"true","children":["$","circle",null,{"cx":"60","cy":"60","r":"50","stroke":"currentColor","strokeWidth":"3","strokeLinecap":"round","strokeDasharray":"280 40"}]}]}],["$","p",null,{"className":"text-xs font-mono uppercase tracking-[0.3em] text-fd-muted-foreground mb-4","children":"404"}],["$","h1",null,{"className":"text-3xl font-semibold mb-3","children":"Page not found"}],["$","p",null,{"className":"text-fd-muted-foreground max-w-sm mb-10","children":"This page doesn't exist, or it may have moved. Try the documentation or head home."}],["$","div",null,{"className":"flex flex-wrap gap-3 justify-center","children":[["$","$L5",null,{"href":"/","className":"inline-flex items-center gap-2 rounded-lg bg-fd-primary text-fd-primary-foreground px-4 py-2 text-sm font-medium hover:opacity-90 transition","children":"Go home"}],["$","$L5",null,{"href":"/docs","className":"inline-flex items-center gap-2 rounded-lg border border-fd-border bg-fd-background px-4 py-2 text-sm font-medium hover:bg-fd-muted transition","children":"Documentation"}],["$","$L5",null,{"href":"/docs/models","className":"inline-flex items-center gap-2 rounded-lg border border-fd-border bg-fd-background px-4 py-2 text-sm font-medium hover:bg-fd-muted transition","children":"Browse models"}]]}],["$","p",null,{"className":"mt-16 text-xs font-mono text-fd-muted-foreground opacity-50","children":"zenlm.org"}]]}],[]],"forbidden":"$undefined","unauthorized":"$undefined"}]}]}]}]]}],{"children":[["$","$1","c",{"children":[null,["$","$L3",null,{"parallelRouterKey":"children","error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L4",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","forbidden":"$undefined","unauthorized":"$undefined"}]]}],{"children":[["$","$1","c",{"children":[null,["$","$L3",null,{"parallelRouterKey":"children","error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L4",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","forbidden":"$undefined","unauthorized":"$undefined"}]]}],{"children":[["$","$1","c",{"children":["$L6",[["$","script","script-0",{"src":"/_next/static/chunks/8de849ca74fc071f.js","async":true,"nonce":"$undefined"}],["$","script","script-1",{"src":"/_next/static/chunks/e62b91212ee7f8ff.js","async":true,"nonce":"$undefined"}],["$","script","script-2",{"src":"/_next/static/chunks/f19fe44237e54646.js","async":true,"nonce":"$undefined"}],["$","script","script-3",{"src":"/_next/static/chunks/cb0a883bafeb6805.js","async":true,"nonce":"$undefined"}]],["$","$L7",null,{"children":["$","$8",null,{"name":"Next.MetadataOutlet","children":"$@9"}]}]]}],{},null,false,false]},null,false,false]},null,false,false]},null,false,false],["$","$1","h",{"children":[null,["$","$La",null,{"children":"$Lb"}],["$","div",null,{"hidden":true,"children":["$","$Lc",null,{"children":["$","$8",null,{"name":"Next.Metadata","children":"$Ld"}]}]}],null]}],false]],"m":"$undefined","G":["$e",[]],"S":true}
|
||
f:I[48068,["/_next/static/chunks/59d0ad1b64f8544e.js","/_next/static/chunks/8de849ca74fc071f.js","/_next/static/chunks/e62b91212ee7f8ff.js","/_next/static/chunks/f19fe44237e54646.js","/_next/static/chunks/cb0a883bafeb6805.js"],"default"]
|
||
6:["$","main",null,{"className":"mx-auto w-full max-w-2xl px-4 py-16","children":[["$","$L5",null,{"href":"/blog","className":"inline-flex items-center gap-1.5 text-sm text-fd-muted-foreground hover:text-fd-foreground mb-10 transition-colors","children":"← Back to Blog"}],["$","div",null,{"className":"mb-8","children":[["$","time",null,{"className":"text-xs font-mono text-fd-muted-foreground uppercase tracking-wider","children":"March 26, 2025"}],["$","h1",null,{"className":"text-3xl font-bold mt-2 mb-3","children":"zen Omni: See, Hear, Talk, Write, Do It All!"}],["$","p",null,{"className":"text-fd-muted-foreground text-lg mb-4","children":"QWEN CHAT HUGGING FACE MODELSCOPE DASHSCOPE GITHUB PAPER DEMO DISCORD"}],["$","div",null,{"className":"flex items-center gap-3 pt-4 border-t border-fd-border","children":[["$","span",null,{"className":"text-sm text-fd-muted-foreground","children":["By ","Zen LM Team"]}],["$","div",null,{"className":"flex gap-1.5 ml-auto","children":[]}]]}]]}],["$","div",null,{"className":"prose dark:prose-invert max-w-none","children":[["$","p",null,{"children":[["$","$Lf",null,{"href":"https://chat.qwenlm.ai","children":"QWEN CHAT"}]," ",["$","$Lf",null,{"href":"https://huggingface.co/Qwen/zen-Omni-7B","children":"HUGGING FACE"}]," ",["$","$Lf",null,{"href":"https://modelscope.cn/models/Qwen/zen-Omni-7B","children":"MODELSCOPE"}]," ",["$","$Lf",null,{"href":"https://help.aliyun.com/zh/model-studio/user-guide/qwen-omni","children":"DASHSCOPE"}]," ",["$","$Lf",null,{"href":"https://github.com/QwenLM/zen-Omni","children":"GITHUB"}]," ",["$","$Lf",null,{"href":"https://github.com/QwenLM/zen-Omni/blob/main/assets/zen_Omni.pdf","children":"PAPER"}]," ",["$","$Lf",null,{"href":"https://huggingface.co/spaces/Qwen/zen-Omni-7B-Demo","children":"DEMO"}]," ",["$","$Lf",null,{"href":"https://discord.com/invite/yPEP2vHTu4","children":"DISCORD"}]]}],"\n",["$","p",null,{"children":["We release ",["$","strong",null,{"children":"zen-Omni"}]," , the new flagship end-to-end multimodal model in the Qwen series. Designed for comprehensive multimodal perception, it seamlessly processes diverse inputs including text, images, audio, and video, while delivering real-time streaming responses through both text generation and natural speech synthesis. To try the latest model, feel free to visit ",["$","$Lf",null,{"href":"https://chat.qwenlm.ai","children":"Qwen Chat"}]," and choose zen-Omni-7B. The model is now openly available on ",["$","$Lf",null,{"href":"https://huggingface.co/Qwen/zen-Omni-7B","children":"Hugging Face"}],", ",["$","$Lf",null,{"href":"https://modelscope.cn/models/Qwen/zen-Omni-7B","children":"ModelScope"}],", ",["$","$Lf",null,{"href":"https://help.aliyun.com/zh/model-studio/user-guide/qwen-omni","children":"DashScope"}],",and ",["$","$Lf",null,{"href":"https://github.com/QwenLM/zen-Omni","children":"GitHub"}],", with technical documentation available in our ",["$","$Lf",null,{"href":"https://github.com/QwenLM/zen-Omni/assets/zen_Omni.pdf","children":"Paper"}],". Experience interactive capabilities through our ",["$","$Lf",null,{"href":"https://huggingface.co/spaces/Qwen/zen-Omni-7B-Demo","children":"Demo"}]," or join our ",["$","$Lf",null,{"href":"https://discord.gg/yPEP2vHTu4","children":"Discord"}]," for discussions."]}],"\n",["$","p",null,{"children":"Key Features:"}],"\n",["$","ul",null,{"children":["\n",["$","li",null,{"children":["\n",["$","p",null,{"children":[["$","strong",null,{"children":"Omni and Novel Architecture"}]," : We propose Thinker-Talker architecture, an end-to-end multimodal model designed to perceive diverse modalities, including text, images, audio, and video, while simultaneously generating text and natural speech responses in a streaming manner. We prpose a novel position embedding, named TMRoPE (Time-aligned Multimodal RoPE), to synchronize the timestamps of video inputs with audio."]}],"\n"]}],"\n",["$","li",null,{"children":["\n",["$","p",null,{"children":[["$","strong",null,{"children":"Real-Time Voice and Video Chat"}]," : Architecture Designed for fully real-time interactions, supporting chunked input and immediate output."]}],"\n"]}],"\n","$L10","\n","$L11","\n","$L12","\n"]}],"\n","$L13","\n","$L14","\n","$L15","\n","$L16","\n","$L17","\n","$L18"]}]]}]
|
||
10:["$","li",null,{"children":["\n",["$","p",null,{"children":[["$","strong",null,{"children":"Natural and Robust Speech Generation"}]," : Surpassing many existing streaming and non-streaming alternatives, demonstrating superior robustness and naturalness in speech generation."]}],"\n"]}]
|
||
11:["$","li",null,{"children":["\n",["$","p",null,{"children":[["$","strong",null,{"children":"Strong Performance Across Modalities"}]," : Exhibiting exceptional performance across all modalities when benchmarked against similarly sized single-modality models. zen-Omni outperforms the similarly sized zen-Audio in audio capabilities and achieves comparable performance to zen-VL-7B."]}],"\n"]}]
|
||
12:["$","li",null,{"children":["\n",["$","p",null,{"children":[["$","strong",null,{"children":"Excellent End-to-End Speech Instruction Following"}]," : zen-Omni shows performance in end-to-end speech instruction following that rivals its effectiveness with text inputs, evidenced by benchmarks such as MMLU and GSM8K."]}],"\n"]}]
|
||
13:["$","h2",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"architecture","children":[["$","a",null,{"data-card":"","href":"#architecture","className":"peer","children":"Architecture"}],["$","svg",null,{"ref":"$undefined","xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
|
||
14:["$","p",null,{"children":"zen-Omni employs Thinker-Talker architecture. Thinker functions like a brain, responsible for processing and understanding inputs from text, audio and video modalities, generating high-level representations and corresponding text. Talker operates like a human mouth, taking in the high-level representations and text produced by the Thinker in a streaming manner, and outputting discrete tokens of speech fluidly. Thinker is a Transformer decoder, accompanied by encoders for audio and image that facilitate information extraction. In contrast, Talker is designed as a dual-track autoregressive Transformer Decoder architecture. During both training and inference, Talker directly receives high-dimensional representations from Thinker and shares all of Thinker’s historical context information. Consequently, the entire architecture operates as a cohesive single model, enabling end-to-end training and inference."}]
|
||
15:["$","h2",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"performance","children":[["$","a",null,{"data-card":"","href":"#performance","className":"peer","children":"Performance"}],["$","svg",null,{"ref":"$undefined","xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
|
||
16:["$","p",null,{"children":"We conducted a comprehensive evaluation of zen-Omni, which demonstrates strong performance across all modalities when compared to similarly sized single-modality models and closed-source models like zen-VL-7B, zen-Audio, and Gemini-1.5-pro. In tasks requiring the integration of multiple modalities, such as OmniBench, zen-Omni achieves state-of-the-art performance. Furthermore, in single-modality tasks, it excels in areas including speech recognition (Common Voice), translation (CoVoST2), audio understanding (MMAU), image reasoning (MMMU, MMStar), video understanding (MVBench), and speech generation (Seed-tts-eval and subjective naturalness)."}]
|
||
17:["$","h2",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"whats-next","children":[["$","a",null,{"data-card":"","href":"#whats-next","className":"peer","children":"What’s Next"}],["$","svg",null,{"ref":"$undefined","xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100","aria-hidden":true,"children":[["$","path","1cjeqo",{"d":"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"}],["$","path","19qd67",{"d":"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"}],"$undefined"]}]]}]
|
||
18:["$","p",null,{"children":"We are eager to hear your feedback and see the innovative applications you create with zen-Omni. In the near future, our goal is to enhance our model’s ability to follow voice commands and improve audio-visual collaborative understanding. Additionally, we strive to integrate more modalities towards an omni-model!"}]
|
||
b:[["$","meta","0",{"charSet":"utf-8"}],["$","meta","1",{"name":"viewport","content":"width=device-width, initial-scale=1"}],["$","meta","2",{"name":"theme-color","media":"(prefers-color-scheme: dark)","content":"#0A0A0A"}],["$","meta","3",{"name":"theme-color","media":"(prefers-color-scheme: light)","content":"#fff"}]]
|
||
9:null
|
||
d:[["$","title","0",{"children":"zen Omni: See, Hear, Talk, Write, Do It All! — Zen LM Blog | Zen LM"}],["$","meta","1",{"name":"description","content":"QWEN CHAT HUGGING FACE MODELSCOPE DASHSCOPE GITHUB PAPER DEMO DISCORD"}],["$","meta","2",{"property":"og:title","content":"Zen LM - Open Foundation Models"}],["$","meta","3",{"property":"og:description","content":"Zen AI model family by Hanzo AI. 14 frontier models from 4B to 1T+ parameters for code, reasoning, vision, and multimodal tasks."}],["$","meta","4",{"property":"og:url","content":"https://zenlm.org"}],["$","meta","5",{"property":"og:site_name","content":"Zen LM"}],["$","meta","6",{"property":"og:type","content":"website"}],["$","meta","7",{"name":"twitter:card","content":"summary_large_image"}],["$","meta","8",{"name":"twitter:site","content":"@zenlmorg"}],["$","meta","9",{"name":"twitter:creator","content":"@zenlmorg"}],["$","meta","10",{"name":"twitter:title","content":"Zen LM - Open Foundation Models"}],["$","meta","11",{"name":"twitter:description","content":"Zen AI model family by Hanzo AI. 14 frontier models from 4B to 1T+ parameters for code, reasoning, vision, and multimodal tasks."}]]
|