按年被提到
20242024 · 3 次2026
大模型与语言模型›大模型预训练与缩放·arXiv:2403.04652 · cs.CL

Yi: Open Foundation Models by 01.AI

01. AI, :, Alex Young, Bei Chen, Chao Li, Chengen Huang, Ge Zhang, Guanwei Zhang, Guoyin Wang, Heng Li, Jiangcheng Zhu, Jianqun Chen 等 33 人 · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 3 人首次 2024-03-08 · 最近 2024-05-13
3不同的人
2活跃月份
3讨论串
373被引(OpenAlex)
arXiv 摘要(候选层不写导读)

We introduce the Yi model family, a series of language and multimodal models that demonstrate strong multi-dimensional capabilities. The Yi model family is based on 6B and 34B pretrained language models, then we extend them to chat models, 200K long context models, depth-upscaled models, and vision-language models. Our base models achieve strong performance on a wide range of benchmarks like MMLU, and our finetuned chat models deliver strong human preference rate on major evaluation platforms like AlpacaEval and Chatbot Arena. Building upon our scalable super-computing infrastructure and the classical transformer architecture, we attribute the performance of Yi models primarily to its data quality resulting from our data-engineering efforts. For pretraining, we construct 3.1 trillion tokens of English and Chinese corpora using a cascaded data deduplication and quality filtering pipeline. For finetuning, we polish a small scale (less than 10K) instruction dataset over multiple iterations such that every single instance has been verified directly by our machine learning engineers. For vision-language, we combine the chat language model with a vision transformer encoder and train the model to align visual representations to the semantic space of the language model. We further extend the context length to 200K through lightweight continual pretraining and demonstrate strong needle-in-a-haystack retrieval performance. We show that extending the depth of the pretrained checkpoint through continual pretraining further improves performance. We believe that given our current results, continuing to scale up model parameters using thoroughly optimized data will lead to even stronger frontier models.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论numpad0 · 2024-05

“Earlier Yi paper indicates it's trained with less than 25% Chinese dataset, contrast to GPT-3 which was 93% English[1][2]. Is that a bug or could there be something inherent to current LLM architecture - like dataset must be 90%+ English to not fall apart? 1: https://arxiv.org/html/2403.04652v1 2: https://github.com/openai/gpt-3/blob/master/dataset_stat…”

被提交为 story · 2 次