Files
zen-blog/blog/qwq-32b.txt

101 lines
54 KiB
Plaintext
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
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","qwq-32b"],"q":"","i":false,"f":[[["",{"children":["blog",{"children":[["slug","qwq-32b","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":[["$","time",null,{"className":"text-xs font-mono text-fd-muted-foreground uppercase tracking-wider","children":"March 5, 2025"}],["$","h1",null,{"className":"text-3xl font-bold mt-2 mb-3","children":"QwQ-32B: Embracing the Power of Reinforcement Learning"}],["$","p",null,{"className":"text-fd-muted-foreground text-lg mb-4","children":"QWEN CHAT Hugging Face ModelScope DEMO DISCORD"}],["$","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://chat.qwen.ai","children":"QWEN CHAT"}]," ",["$","$Lf",null,{"href":"https://huggingface.co/Qwen/QwQ-32B","children":"Hugging Face"}]," ",["$","$Lf",null,{"href":"https://modelscope.cn/models/Qwen/QwQ-32B","children":"ModelScope"}]," ",["$","$Lf",null,{"href":"https://huggingface.co/spaces/Qwen/QwQ-32B-Demo","children":"DEMO"}]," ",["$","$Lf",null,{"href":"https://discord.gg/yPEP2vHTu4","children":"DISCORD"}]]}],"\n",["$","p",null,{"children":"Scaling Reinforcement Learning (RL) has the potential to enhance model performance beyond conventional pretraining and post-training methods. Recent studies have demonstrated that RL can significantly improve the reasoning capabilities of models. For instance, DeepSeek R1 has achieved state-of-the-art performance by integrating cold-start data and multi-stage training, enabling deep thinking and complex reasoning."}],"\n",["$","p",null,{"children":"Our research explores the scalability of Reinforcement Learning (RL) and its impact on enhancing the intelligence of large language models. We are excited to introduce QwQ-32B, a model with 32 billion parameters that achieves performance comparable to DeepSeek-R1, which boasts 671 billion parameters (with 37 billion activated). This remarkable outcome underscores the effectiveness of RL when applied to robust foundation models pretrained on extensive world knowledge. Furthermore, we have integrated agent-related capabilities into the reasoning model, enabling it to think critically while utilizing tools and adapting its reasoning based on environmental feedback. These advancements not only demonstrate the transformative potential of RL but also pave the way for further innovations in the pursuit of artificial general intelligence."}],"\n",["$","p",null,{"children":["QwQ-32B is open-weight in ",["$","$Lf",null,{"href":"https://huggingface.co/Qwen/QwQ-32B","children":"Hugging Face"}]," and ",["$","$Lf",null,{"href":"https://modelscope.cn/models/Qwen/QwQ-32B","children":"ModelScope"}]," under the Apache 2.0 license and is accessible via ",["$","$Lf",null,{"href":"https://chat.qwen.ai/?models=zen-Plus","children":"Qwen Chat"}],"."]}],"\n",["$","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"}],"$L10","$undefined"]}]]}],"\n","$L11","\n","$L12","\n","$L13","\n","$L14","\n","$L15","\n","$L16","\n","$L17","\n","$L18","\n","$L19"]}]]}]
1a:I[51504,["/_next/static/chunks/59d0ad1b64f8544e.js","/_next/static/chunks/8de849ca74fc071f.js","/_next/static/chunks/e62b91212ee7f8ff.js","/_next/static/chunks/f19fe44237e54646.js","/_next/static/chunks/cb0a883bafeb6805.js"],"CodeBlock"]
1c:I[51504,["/_next/static/chunks/59d0ad1b64f8544e.js","/_next/static/chunks/8de849ca74fc071f.js","/_next/static/chunks/e62b91212ee7f8ff.js","/_next/static/chunks/f19fe44237e54646.js","/_next/static/chunks/cb0a883bafeb6805.js"],"Pre"]
10:["$","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"}]
11:["$","p",null,{"children":"QwQ-32B is evaluated across a range of benchmarks designed to assess its mathematical reasoning, coding proficiency, and general problem-solving capabilities. The results below highlight QwQ-32B’s performance in comparison to other leading models, including DeepSeek-R1-Distilled-Qwen-32B, DeepSeek-R1-Distilled-Llama-70B, o1-mini, and the original DeepSeek-R1."}]
12:["$","h2",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"reinforcement-learning","children":[["$","a",null,{"data-card":"","href":"#reinforcement-learning","className":"peer","children":"Reinforcement Learning"}],["$","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"]}]]}]
13:["$","p",null,{"children":"We began with a cold-start checkpoint and implemented a reinforcement learning (RL) scaling approach driven by outcome-based rewards. In the initial stage, we scale RL specifically for math and coding tasks. Rather than relying on traditional reward models, we utilized an accuracy verifier for math problems to ensure the correctness of final solutions and a code execution server to assess whether the generated codes successfully pass predefined test cases. As training episodes progress, performance in both domains shows continuous improvement. After the first stage, we add another stage of RL for general capabilities. It is trained with rewards from general reward model and some rule-based verifiers. We find that this stage of RL training with a small amount of steps can increase the performance of other general capabilities, such as instruction following, alignment with human preference, and agent performance, without significant performance drop in math and coding."}]
14:["$","h2",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"use-qwq-32b","children":[["$","a",null,{"data-card":"","href":"#use-qwq-32b","className":"peer","children":"Use QwQ-32B"}],["$","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"]}]]}]
15:["$","p",null,{"children":"Below are brief examples demonstrating how to use QwQ-32B via Hugging Face Transformers and Alibaba Cloud DashScope API."}]
1b:T5c0,<svg viewBox="0 0 24 24"><path d="M14.25.18l.9.2.73.26.59.3.45.32.34.34.25.34.16.33.1.3.04.26.02.2-.01.13V8.5l-.05.63-.13.55-.21.46-.26.38-.3.31-.33.25-.35.19-.35.14-.33.1-.3.07-.26.04-.21.02H8.77l-.69.05-.59.14-.5.22-.41.27-.33.32-.27.35-.2.36-.15.37-.1.35-.07.32-.04.27-.02.21v3.06H3.17l-.21-.03-.28-.07-.32-.12-.35-.18-.36-.26-.36-.36-.35-.46-.32-.59-.28-.73-.21-.88-.14-1.05-.05-1.23.06-1.22.16-1.04.24-.87.32-.71.36-.57.4-.44.42-.33.42-.24.4-.16.36-.1.32-.05.24-.01h.16l.06.01h8.16v-.83H6.18l-.01-2.75-.02-.37.05-.34.11-.31.17-.28.25-.26.31-.23.38-.2.44-.18.51-.15.58-.12.64-.1.71-.06.77-.04.84-.02 1.27.05zm-6.3 1.98l-.23.33-.08.41.08.41.23.34.33.22.41.09.41-.09.33-.22.23-.34.08-.41-.08-.41-.23-.33-.33-.22-.41-.09-.41.09zm13.09 3.95l.28.06.32.12.35.18.36.27.36.35.35.47.32.59.28.73.21.88.14 1.04.05 1.23-.06 1.23-.16 1.04-.24.86-.32.71-.36.57-.4.45-.42.33-.42.24-.4.16-.36.09-.32.05-.24.02-.16-.01h-8.22v.82h5.84l.01 2.76.02.36-.05.34-.11.31-.17.29-.25.25-.31.24-.38.2-.44.17-.51.15-.58.13-.64.09-.71.07-.77.04-.84.01-1.27-.04-1.07-.14-.9-.2-.73-.25-.59-.3-.45-.33-.34-.34-.25-.34-.16-.33-.1-.3-.04-.25-.02-.2.01-.13v-5.34l.05-.64.13-.54.21-.46.26-.38.3-.32.33-.24.35-.2.35-.14.33-.1.3-.06.26-.04.21-.02.13-.01h5.84l.69-.05.59-.14.5-.21.41-.28.33-.32.27-.35.2-.36.15-.36.1-.35.07-.32.04-.28.02-.21V6.07h2.09l.14.01zm-6.47 14.25l-.23.33-.08.41.08.41.23.33.33.23.41.08.41-.08.33-.23.23-.33.08-.41-.08-.41-.23-.33-.33-.23-.41-.08-.41.08z" fill="currentColor" /></svg>16:["$","$L1a",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":"$1b","children":["$","$L1c",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line"}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" from"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" transformers "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"import"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" AutoModelForCausalLM, AutoTokenizer"}]]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" model_name "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" \"Qwen/QwQ-32B\""}]]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" model "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" AutoModelForCausalLM.from_pretrained("}]]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" model_name,"}]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":" torch_dtype"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"auto\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":","}]]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":" device_map"}],"$L1d","$L1e"]}],"\n","$L1f","\n","$L20","\n","$L21","\n","$L22","\n","$L23","\n","$L24","\n","$L25","\n","$L26","\n","$L27","\n","$L28","\n","$L29","\n","$L2a","\n","$L2b","\n","$L2c","\n","$L2d","\n","$L2e","\n","$L2f","\n","$L30","\n","$L31","\n","$L32","\n","$L33","\n","$L34","\n","$L35","\n","$L36","\n","$L37","\n","$L38"]}]}]}]
39:T5c0,<svg viewBox="0 0 24 24"><path d="M14.25.18l.9.2.73.26.59.3.45.32.34.34.25.34.16.33.1.3.04.26.02.2-.01.13V8.5l-.05.63-.13.55-.21.46-.26.38-.3.31-.33.25-.35.19-.35.14-.33.1-.3.07-.26.04-.21.02H8.77l-.69.05-.59.14-.5.22-.41.27-.33.32-.27.35-.2.36-.15.37-.1.35-.07.32-.04.27-.02.21v3.06H3.17l-.21-.03-.28-.07-.32-.12-.35-.18-.36-.26-.36-.36-.35-.46-.32-.59-.28-.73-.21-.88-.14-1.05-.05-1.23.06-1.22.16-1.04.24-.87.32-.71.36-.57.4-.44.42-.33.42-.24.4-.16.36-.1.32-.05.24-.01h.16l.06.01h8.16v-.83H6.18l-.01-2.75-.02-.37.05-.34.11-.31.17-.28.25-.26.31-.23.38-.2.44-.18.51-.15.58-.12.64-.1.71-.06.77-.04.84-.02 1.27.05zm-6.3 1.98l-.23.33-.08.41.08.41.23.34.33.22.41.09.41-.09.33-.22.23-.34.08-.41-.08-.41-.23-.33-.33-.22-.41-.09-.41.09zm13.09 3.95l.28.06.32.12.35.18.36.27.36.35.35.47.32.59.28.73.21.88.14 1.04.05 1.23-.06 1.23-.16 1.04-.24.86-.32.71-.36.57-.4.45-.42.33-.42.24-.4.16-.36.09-.32.05-.24.02-.16-.01h-8.22v.82h5.84l.01 2.76.02.36-.05.34-.11.31-.17.29-.25.25-.31.24-.38.2-.44.17-.51.15-.58.13-.64.09-.71.07-.77.04-.84.01-1.27-.04-1.07-.14-.9-.2-.73-.25-.59-.3-.45-.33-.34-.34-.25-.34-.16-.33-.1-.3-.04-.25-.02-.2.01-.13v-5.34l.05-.64.13-.54.21-.46.26-.38.3-.32.33-.24.35-.2.35-.14.33-.1.3-.06.26-.04.21-.02.13-.01h5.84l.69-.05.59-.14.5-.21.41-.28.33-.32.27-.35.2-.36.15-.36.1-.35.07-.32.04-.28.02-.21V6.07h2.09l.14.01zm-6.47 14.25l-.23.33-.08.41.08.41.23.33.33.23.41.08.41-.08.33-.23.23-.33.08-.41-.08-.41-.23-.33-.33-.23-.41-.08-.41.08z" fill="currentColor" /></svg>17:["$","$L1a",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":"$39","children":["$","$L1c",null,{"children":["$","code",null,{"children":[["$","span",null,{"className":"line"}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" from"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" openai "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"import"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" OpenAI"}]]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" import"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" os"}]]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#6A737D","--shiki-dark":"#6A737D"},"children":" # Initialize OpenAI client"}]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" client "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" OpenAI("}]]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#6A737D","--shiki-dark":"#6A737D"},"children":" # If the environment variable is not configured, replace with your API Key: api_key=\"sk-xxx\""}]}],"\n",["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#6A737D","--shiki-dark":"#6A737D"},"children":" # How to get an API Key:https://help.aliyun.com/zh/model-studio/developer-reference/get-api-key"}]}],"\n",["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":" api_key"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"os.getenv("}],"$L3a","$L3b"]}],"\n","$L3c","\n","$L3d","\n","$L3e","\n","$L3f","\n","$L40","\n","$L41","\n","$L42","\n","$L43","\n","$L44","\n","$L45","\n","$L46","\n","$L47","\n","$L48","\n","$L49","\n","$L4a","\n","$L4b","\n","$L4c","\n","$L4d","\n","$L4e","\n","$L4f","\n","$L50","\n","$L51","\n","$L52","\n","$L53","\n","$L54","\n","$L55","\n","$L56","\n","$L57","\n","$L58","\n","$L59","\n","$L5a","\n","$L5b","\n","$L5c","\n","$L5d","\n","$L5e","\n","$L5f","\n","$L60","\n","$L61","\n","$L62","\n","$L63","\n","$L64"]}]}]}]
18:["$","h2",null,{"className":"flex scroll-m-28 flex-row items-center gap-2","id":"future-work","children":[["$","a",null,{"data-card":"","href":"#future-work","className":"peer","children":"Future Work"}],["$","svg",null,{"ref":"$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"}],"$undefined"]}]]}]
19:["$","p",null,{"children":"This marks Qwen’s initial step in scaling Reinforcement Learning (RL) to enhance reasoning capabilities. Through this journey, we have not only witnessed the immense potential of scaled RL but also recognized the untapped possibilities within pretrained language models. As we work towards developing the next generation of Qwen, we are confident that combining stronger foundation models with RL powered by scaled computational resources will propel us closer to achieving Artificial General Intelligence (AGI). Additionally, we are actively exploring the integration of agents with RL to enable long-horizon reasoning, aiming to unlock greater intelligence with inference time scaling."}]
1d:["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}]
1e:["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"auto\""}]
1f:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" )"}]}]
20:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" tokenizer "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" AutoTokenizer.from_pretrained(model_name)"}]]}]
21:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]
22:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" prompt "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" \"How many r's are in the word "}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"\\\""}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"strawberry"}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"\\\""}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\""}]]}]
23:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" messages "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" ["}]]}]
24:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" {"}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"role\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":": "}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"user\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":", "}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"content\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":": prompt}"}]]}]
25:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" ]"}]}]
26:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" text "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" tokenizer.apply_chat_template("}]]}]
27:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" messages,"}]}]
28:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":" tokenize"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"False"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":","}]]}]
29:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":" add_generation_prompt"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"True"}]]}]
2a:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" )"}]}]
2b:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]
2c:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" model_inputs "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" tokenizer([text], "}],["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":"return_tensors"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"pt\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":").to(model.device)"}]]}]
2d:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]
2e:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" generated_ids "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" model.generate("}]]}]
2f:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" **"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"model_inputs,"}]]}]
30:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":" max_new_tokens"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"32768"}]]}]
31:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" )"}]}]
32:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" generated_ids "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" ["}]]}]
33:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" output_ids["}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"len"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"(input_ids):] "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"for"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" input_ids, output_ids "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"in"}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" zip"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"(model_inputs.input_ids, generated_ids)"}]]}]
34:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" ]"}]}]
35:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]
36:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" response "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" tokenizer.batch_decode(generated_ids, "}],["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":"skip_special_tokens"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"True"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":")["}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"0"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"]"}]]}]
37:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" print"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"(response)"}]]}]
38:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]
3a:["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"DASHSCOPE_API_KEY\""}]
3b:["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"),"}]
3c:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":" base_url"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"https://dashscope.aliyuncs.com/compatible-mode/v1\""}]]}]
3d:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" )"}]}]
3e:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]
3f:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" reasoning_content "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" \"\""}]]}]
40:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" content "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" \"\""}]]}]
41:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]
42:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" is_answering "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" False"}]]}]
43:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]
44:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" completion "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" client.chat.completions.create("}]]}]
45:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":" model"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"qwq-32b\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":","}]]}]
46:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":" messages"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"["}]]}]
47:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" {"}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"role\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":": "}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"user\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":", "}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"content\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":": "}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\"Which is larger, 9.9 or 9.11?\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"}"}]]}]
48:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" ],"}]}]
49:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":" stream"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"True"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":","}]]}]
4a:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#6A737D","--shiki-dark":"#6A737D"},"children":" # Uncomment the following line to return token usage in the last chunk"}]}]
4b:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#6A737D","--shiki-dark":"#6A737D"},"children":" # stream_options={"}]}]
4c:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#6A737D","--shiki-dark":"#6A737D"},"children":" # \"include_usage\": True"}]}]
4d:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#6A737D","--shiki-dark":"#6A737D"},"children":" # }"}]}]
4e:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" )"}]}]
4f:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]
50:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" print"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"("}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\""}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"\\n"}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\""}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" +"}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" \"=\""}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" *"}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" 20"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" +"}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" \"reasoning content\""}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" +"}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" \"=\""}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" *"}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" 20"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" +"}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" \""}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"\\n"}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":")"}]]}]
51:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]
52:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" for"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" chunk "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"in"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" completion:"}]]}]
53:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#6A737D","--shiki-dark":"#6A737D"},"children":" # If chunk.choices is empty, print usage"}]}]
54:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" if"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" not"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" chunk.choices:"}]]}]
55:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" print"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"("}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\""}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"\\n"}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"Usage:\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":")"}]]}]
56:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" print"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"(chunk.usage)"}]]}]
57:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" else"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":":"}]]}]
58:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" delta "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" chunk.choices["}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"0"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"].delta"}]]}]
59:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#6A737D","--shiki-dark":"#6A737D"},"children":" # Print reasoning content"}]}]
5a:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" if"}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" hasattr"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"(delta, "}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"'reasoning_content'"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":") "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"and"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" delta.reasoning_content "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"is"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" not"}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" None"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":":"}]]}]
5b:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" print"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"(delta.reasoning_content, "}],["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":"end"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"''"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":", "}],["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":"flush"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"True"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":")"}]]}]
5c:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" reasoning_content "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"+="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" delta.reasoning_content"}]]}]
5d:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" else"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":":"}]]}]
5e:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" if"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" delta.content "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"!="}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" \"\""}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" and"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" is_answering "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"is"}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" False"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":":"}]]}]
5f:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" print"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"("}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\""}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"\\n"}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\""}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" +"}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" \"=\""}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" *"}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" 20"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" +"}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" \"content\""}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" +"}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" \"=\""}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" *"}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" 20"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":" +"}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":" \""}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"\\n"}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"\""}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":")"}]]}]
60:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" is_answering "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" True"}]]}]
61:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#6A737D","--shiki-dark":"#6A737D"},"children":" # Print content"}]}]
62:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":" print"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":"(delta.content, "}],["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":"end"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#032F62","--shiki-dark":"#9ECBFF"},"children":"''"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":", "}],["$","span",null,{"style":{"--shiki-light":"#E36209","--shiki-dark":"#FFAB70"},"children":"flush"}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"="}],["$","span",null,{"style":{"--shiki-light":"#005CC5","--shiki-dark":"#79B8FF"},"children":"True"}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":")"}]]}]
63:["$","span",null,{"className":"line","children":[["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" content "}],["$","span",null,{"style":{"--shiki-light":"#D73A49","--shiki-dark":"#F97583"},"children":"+="}],["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" delta.content"}]]}]
64:["$","span",null,{"className":"line","children":["$","span",null,{"style":{"--shiki-light":"#24292E","--shiki-dark":"#E1E4E8"},"children":" "}]}]
b:[["$","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":"QwQ-32B: Embracing the Power of Reinforcement Learning — Zen LM Blog | Zen LM"}],["$","meta","1",{"name":"description","content":"QWEN CHAT Hugging Face ModelScope DEMO DISCORD"}],["$","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."}]]