Files
zen-blog/blog/qwen1.5-110b.txt

33 lines
20 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","qwen1.5-110b"],"q":"","i":false,"f":[[["",{"children":["blog",{"children":[["slug","qwen1.5-110b","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":[["$","time",null,{"className":"text-xs font-mono text-fd-muted-foreground uppercase tracking-wider","children":"April 24, 2024"}],["$","h1",null,{"className":"text-3xl font-bold mt-2 mb-3","children":"Qwen1.5-110B: The First 100B+ Model of the Qwen1.5 Series"}],["$","p",null,{"className":"text-fd-muted-foreground text-lg mb-4","children":"GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD"}],["$","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://github.com/QwenLM/Qwen1.5","children":"GITHUB"}]," ",["$","$Lf",null,{"href":"https://huggingface.co/Qwen","children":"HUGGING FACE"}]," ",["$","$Lf",null,{"href":"https://modelscope.cn/organization/qwen","children":"MODELSCOPE"}]," ",["$","$Lf",null,{"href":"https://huggingface.co/spaces/Qwen/Qwen1.5-110B-Chat-Demo","children":"DEMO"}]," ",["$","$Lf",null,{"href":"https://discord.gg/yPEP2vHTu4","children":"DISCORD"}]]}],"\n",["$","h1",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"introduction","children":[["$","a",null,{"data-card":"","href":"#introduction","className":"peer","children":"Introduction"}],["$","svg",null,{"ref":"$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"}],"$undefined"]}]]}],"\n",["$","p",null,{"children":"Recently we have witnessed a burst of large-scale models with over 100 billion parameters in the opensource community. These models have demonstrated remarkable performance in both benchmark evaluation and chatbot arena. Today, we release the first 100B+ model of the Qwen1.5 series, Qwen1.5-110B, which achieves comparable performance with Meta-Llama3-70B in the base model evaluation, and outstanding performance in the chat evaluation, including MT-Bench and AlpacaEval 2.0."}],"\n",["$","h1",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"model-features","children":[["$","a",null,{"data-card":"","href":"#model-features","className":"peer","children":"Model Features"}],["$","svg",null,{"ref":"$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"}],"$undefined"]}]]}],"\n",["$","p",null,{"children":"Qwen1.5-110B is similar to other Qwen1.5 models and built with the same Transformer decoder architecture. It consists of grouped query attention (GQA) and it can be efficient in model serving. The model supports the context length 32K tokens, and the model is still multilingual, supporting a large number of languages including English, Chinese, French, Spanish, German, Russian, Korean, Japanese, Vietnamese, Arabic, etc."}],"\n","$L10","\n","$L11","\n","$L12","\n","$L13","\n","$L14","\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n","$L15","\n","$L16","\n","$L17","\n","$L18","\n","$L19","\n","$L1a","\n","$L1b","\n","$L1c"]}]]}]
1d:I[51504,["/_next/static/chunks/59d0ad1b64f8544e.js","/_next/static/chunks/8de849ca74fc071f.js","/_next/static/chunks/e62b91212ee7f8ff.js","/_next/static/chunks/f19fe44237e54646.js","/_next/static/chunks/cb0a883bafeb6805.js"],"CodeBlock"]
1e:I[51504,["/_next/static/chunks/59d0ad1b64f8544e.js","/_next/static/chunks/8de849ca74fc071f.js","/_next/static/chunks/e62b91212ee7f8ff.js","/_next/static/chunks/f19fe44237e54646.js","/_next/static/chunks/cb0a883bafeb6805.js"],"Pre"]
10:["$","h1",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"model-quality","children":[["$","a",null,{"data-card":"","href":"#model-quality","className":"peer","children":"Model Quality"}],["$","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"]}]]}]
11:["$","p",null,{"children":"We conduct a series of evaluations for the base language models, and we compare with Meta-Llama3-70B, the recent SOTA language model as well as Mixtral-8x22B."}]
12:["$","p",null,{"children":["| Qwen1.5-110B| Qwen1.5-72B| Llama-3-70B| Mixtral-8x22B",["$","br",null,{}],"\n---|---|---|---|---",["$","br",null,{}],"\nMMLU| 80.4| 77.5| 79.5| 77.8",["$","br",null,{}],"\nTheoremQA| 34.9| 29.3| 32.0| 35.9",["$","br",null,{}],"\nGPQA| 35.9| 36.3| 36.4| 34.3",["$","br",null,{}],"\nHellaswag| 87.5| 86.0| 88.0| 88.7",["$","br",null,{}],"\nBBH| 74.8| 65.5| 76.6| 69.2",["$","br",null,{}],"\nARC-C| 69.6| 65.9| 68.8| 70.7",["$","br",null,{}],"\nGSM8K| 85.4| 79.5| 79.2| 78.6",["$","br",null,{}],"\nMATH| 49.6| 34.1| 41.0| 41.7",["$","br",null,{}],"\nHumanEval| 52.4| 41.5| 45.7| 45.1",["$","br",null,{}],"\nMBPP| 58.1| 53.4| 55.1| 71.2"]}]
13:["$","p",null,{"children":"The above results show that the new 110B model is at least competitive with the Llama-3-70B model in terms of base capabilities. In terms of this model, we did not change the pretraining and posttraining recipes drastically, and thus we believe that the performance improvement compared with 72B comes from increasing model size."}]
14:["$","p",null,{"children":"We also test the chat models on MT-Bench and AlpacaEval 2.0."}]
15:["$","div",null,{"className":"relative overflow-auto prose-no-margin my-6","children":["$","table",null,{"children":[["$","thead",null,{"children":["$","tr",null,{"children":[["$","th",null,{"children":"Models"}],["$","th",null,{"children":"MT-Bench"}],["$","th",null,{"children":"AlpacaEval 2.0"}]]}]}],["$","tbody",null,{"children":[["$","tr",null,{"children":[["$","td",null,{"children":"Avg. Score"}],["$","td",null,{"children":"LC Win Rate"}],["$","td",null,{}]]}],["$","tr",null,{"children":[["$","td",null,{"children":"Llama-3-70B-Instruct"}],["$","td",null,{"children":"8.85"}],["$","td",null,{"children":"34.40"}]]}],["$","tr",null,{"children":[["$","td",null,{"children":"Qwen1.5-72B-Chat"}],["$","td",null,{"children":"8.61"}],["$","td",null,{"children":"36.60"}]]}],["$","tr",null,{"children":[["$","td",null,{"children":"Qwen1.5-110B-Chat"}],["$","td",null,{"children":"8.88"}],["$","td",null,{"children":"43.90"}]]}]]}]]}]}]
16:["$","p",null,{"children":"Compared with the previously released 72B model, on the two benchmark evaluation for chat models the 110B performs significantly better. The consistent improvement in the evaluation indicates that stronger and larger base language models can lead to better chat models even without changing the post-training recipes much."}]
17:["$","h1",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"develop-with-qwen15-110b","children":[["$","a",null,{"data-card":"","href":"#develop-with-qwen15-110b","className":"peer","children":"Develop with Qwen1.5-110B"}],["$","svg",null,{"ref":"$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 advise you to read our blog for ",["$","$Lf",null,{"href":"https://qwenlm.github.io/blog/qwen1.5/","children":"Qwen1.5"}]," to figure out the usages with Transformers, vLLM, llama.cpp, Ollama, LMStudio, SkyPilot, Axolotl, LLaMA-Factory, etc."]}]
19:["$","h1",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"conclusion","children":[["$","a",null,{"data-card":"","href":"#conclusion","className":"peer","children":"Conclusion"}],["$","svg",null,{"ref":"$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"}],"$undefined"]}]]}]
1a:["$","p",null,{"children":"The Qwen1.5-110B is the largest model in the Qwen1.5 series, and it is also the first one with over 100 billion parameters in the series. It demonstrates competitive performance against the very recently released SOTA model Llama-3-70B and it is significantly better than the 72B model. This tells us that there is still a lot of room in model size scaling for better performance. While the releease of Llama-3 indicates the significance of data scaling to an extremely large scale, we believe we can get the best of both worlds by scaling both data and model size in our future release. Stay tuned for zen!"}]
1b:["$","h1",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"citation","children":[["$","a",null,{"data-card":"","href":"#citation","className":"peer","children":"Citation"}],["$","svg",null,{"ref":"$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"}],"$undefined"]}]]}]
1c:["$","$L1d",null,{"className":"shiki shiki-themes github-light github-dark","style":{"--shiki-light":"#24292e","--shiki-dark":"#e1e4e8","--shiki-light-bg":"#fff","--shiki-dark-bg":"#24292e"},"tabIndex":"0","icon":"<svg viewBox=\"0 0 24 24\"><path d=\"M 6,1 C 4.354992,1 3,2.354992 3,4 v 16 c 0,1.645008 1.354992,3 3,3 h 12 c 1.645008,0 3,-1.354992 3,-3 V 8 7 A 1.0001,1.0001 0 0 0 20.707031,6.2929687 l -5,-5 A 1.0001,1.0001 0 0 0 15,1 h -1 z m 0,2 h 7 v 3 c 0,1.645008 1.354992,3 3,3 h 3 v 11 c 0,0.564129 -0.435871,1 -1,1 H 6 C 5.4358712,21 5,20.564129 5,20 V 4 C 5,3.4358712 5.4358712,3 6,3 Z M 15,3.4140625 18.585937,7 H 16 C 15.435871,7 15,6.5641288 15,6 Z\" fill=\"currentColor\" /></svg>","children":["$","$L1e",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line","children":["$","span",null,{}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" @misc{qwen1.5,"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" title = {Introducing Qwen1.5},"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" url = {https://qwenlm.github.io/blog/qwen1.5/},"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" author = {Qwen Team},"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" month = {February},"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" year = {2024}"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" }"}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"children":" "}]}]]}]}]}]
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:[["$","title","0",{"children":"Qwen1.5-110B: The First 100B+ Model of the Qwen1.5 Series — Zen LM Blog | Zen LM"}],["$","meta","1",{"name":"description","content":"GITHUB HUGGING FACE MODELSCOPE 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."}]]