|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Llada的研究人员报告了他们的80亿参数模型的性能与各种基准的Llama3 8b相似

Large language models (LLMs) are typically bottlenecked by speed, especially when compared to smaller models. However, new diffusion-based models have reportedly achieved performance faster than or comparable to similarly sized conventional models while also being significantly faster.
大型语言模型(LLM)通常是通过速度瓶颈的,尤其是与较小的型号相比。但是,据报道,基于扩散的新模型的性能比相似大小的常规模型更快或相当,同时也要快得多。
LLaDA, a 7-billion parameter language model from researchers at the University of Science and Technology of China, performs similarly to LLaMA3 8B across various benchmarks.
兰达(Llada)是中国科学技术研究人员的70亿个参数语言模型,在各种基准测试中与Llama3 8B的表现相似。
According to Inception, an AI startup focused on efficient deep learning, LLaDA achieves competitive results on tasks like MMLU, ARC, and GSM8K.
根据Inception,一家专注于有效深度学习的AI初创公司在MMLU,ARC和GSM8K等任务上取得了竞争成果。
But when comparing the speed of an 8-billion parameter LLaDA model to an 8-billion parameter LLaMA3 model, LLaDA generates 1,024 tokens per second on an Nvidia H100, whereas LLaMA3 generates about 60 tokens per second. This difference in throughput is roughly 17x.
但是,将80亿个参数LLADA模型与80亿参数Llama3模型进行比较时,LLADA在NVIDIA H100上每秒产生1,024个令牌,而Llama3每秒产生约60个令牌。吞吐量的这种差异约为17倍。
LLaDA's researchers claim this level of performance is possible with models as small as 3 billion parameters.
LLADA的研究人员声称,这种绩效水平是可能的,模型小于30亿个参数。
Compared to GPT-4o Mini, which operates at 59 tokens per second, Mercury Coder Mini scores 88.0 percent on HumanEval and 77.1 percent on MBPP—comparable to GPT-4o Mini—while reportedly operating at 1,109 tokens per second. This represents an 18x speed advantage over GPT-4o Mini.
与GPT-4O MINI相比,该Mini的运行量为每秒59个令牌,汞编码器Mini在HOMANEVAL上得分为88.0%,MBPP的分数为77.1%,与GPT-4O Mini相吻合,据报道以每秒1,109个代币运行。这代表了比GPT-4O Mini具有18倍的速度优势。
Mercury's documentation states its models run "at over 1,000 tokens/sec on Nvidia H100s, a speed previously possible only using custom chips" from specialized hardware providers like Groq, Cerebras, and SambaNova. When compared to other speed-optimized models, the claimed advantage remains significant—Mercury Coder Mini is reportedly about 5.5x faster than Gemini 2.0 Flash-Lite (201 tokens/second) and 18x faster than Claude 3.5 Haiku (61 tokens/second).
水星的文档指出,其模型“在NVIDIA H100上以1000多个令牌/秒为单位,以前只能使用定制芯片从Groq,Cerebras和Sambanova等专业硬件提供商使用自定义芯片”。与其他速度优化模型相比,声称的优势仍然显着 - 据报道,MINI的MINI比Gemini 2.0 Flash-Lite(201/秒/秒)快约5.5倍,比Claude 3.5 Haiku(61个令牌/秒)快18倍。
According to Inception, Mercury Coder Mini also outperforms smaller models from GPT-3.5 series and PaLM 2 series at comparable speed.
根据Inception,水星编码器Mini还以可比的速度优于GPT-3.5系列和Palm 2系列的较小型号。
At 1,024 tokens per second, LLaDA is faster than smaller models from GPT-3.5 series and PaLM 2 series at comparable speed. At 201 tokens per second, Gemini 2.0 Flash-Lite has better performance at HumanEval and worse performance at MBPP than Mercury Coder Mini. At 61 tokens per second, Claude 3.5 Haiku has better performance at both HumanEval and MBPP than Mercury Coder Mini.
LLADA在每秒1,024个令牌时的速度比GPT-3.5系列和Palm 2系列的较小型号以可比的速度快。 Gemini 2.0 Flash-lite在每秒的201个令牌上,在HOMANEVAL上的性能要好,而MBPP的性能比Mercury Coder Mini更差。 Claude 3.5 Haiku在每秒61个令牌时,在HumaneVal和MBPP的性能都比Mercury Coder Mini更好。
Opening a potential new frontier in LLMs
在LLMS开设潜在的新边界
Diffusion models do involve some trade-offs. They typically need multiple forward passes through the network to generate a complete response, unlike traditional models that need just one pass per token. However, because diffusion models process all tokens in parallel, they achieve higher throughput despite this overhead.
扩散模型确实涉及一些权衡。他们通常需要多个向前通过网络来产生完整的响应,这与传统模型只需要一个令牌,而传统模型也只需一个代币。但是,由于扩散模型并行处理所有令牌,但尽管开销,它们达到了更高的吞吐量。
Inception thinks the speed advantages could impact code completion tools where instant response may affect developer productivity, conversational AI applications, resource-limited environments like mobile applications, and AI agents that need to respond quickly.
Inception认为,速度优势可能会影响代码完成工具,即即时响应可能会影响开发人员生产力,对话AI应用程序,资源有限的环境(例如移动应用程序)以及需要快速响应的AI代理。
If diffusion-based language models maintain quality while improving speed, they might change how AI text generation develops. So far, AI researchers have been open to new approaches.
如果基于扩散的语言模型在提高速度的同时保持质量,则可能会改变AI文本生成的发展方式。到目前为止,AI研究人员已经接受了新方法。
Independent AI researcher Simon Willison told Ars Technica, "I love that people are experimenting with alternative architectures to transformers, it's yet another illustration of how much of the space of LLMs we haven't even started to explore yet."
独立的AI研究员西蒙·威利森(Simon Willison)告诉ARS Technica:“我喜欢人们正在尝试使用替代架构到变形金刚,这是我们甚至还没有开始探索的LLMS空间的另一个说明。”
On X, former OpenAI researcher Andrej Karpathy wrote about Inception, "This model has the potential to be different, and possibly showcase new, unique psychology, or new strengths and weaknesses. I encourage people to try it out!"
在X上,前Openai研究员Andrej Karpathy写道:“该模型有可能与众不同,可能展示新的,独特的心理学或新的优势和劣势。我鼓励人们尝试一下!”
Questions remain about whether larger diffusion models can match the performance of models like GPT-4o and Claude 3.7 Sonnet, and if the approach can handle increasingly complex simulated reasoning tasks. For now, these models offer an alternative for smaller AI language models that doesn't seem to sacrifice capability for speed.
关于较大的扩散模型是否可以与GPT-4O和Claude 3.7十四行诗等模型的性能相匹配的问题仍然存在问题,并且该方法是否可以处理日益复杂的模拟推理任务。目前,这些模型为较小的AI语言模型提供了一种替代方案,似乎并没有为速度牺牲能力。
You can try Mercury Coder yourself on Inception's demo site, and you can download code for LLaDA or try a demo on Hugging Face.
您可以在Inception的演示网站上尝试Mercury编码器,并且可以下载llada的代码,也可以在拥抱面孔时尝试演示。
免责声明:info@kdj.com
所提供的信息并非交易建议。根据本文提供的信息进行的任何投资,kdj.com不承担任何责任。加密货币具有高波动性,强烈建议您深入研究后,谨慎投资!
如您认为本网站上使用的内容侵犯了您的版权,请立即联系我们(info@kdj.com),我们将及时删除。
-
-
-
-
-
-
- 比特币零售需求因价格下跌而暴跌,技术指标确认看跌趋势
- 2026-11-14 15:45:01
- Bitcoin零售需求锐减近10%至3月以来最低水平,伴随价格跌破7万美元,技术指标指向持续看跌。
-
-
-
- XRP 价格预测:1000 美元会让每个人都变得富有吗?技术面建议值得关注的关键水平
- 2026-11-14 04:05:01
- 分析 XRP 以 1,000 美元创造百万富翁的潜力以及价格预测的关键技术水平。

































