We introduce InternLM-XComposer2, a cutting-edge vision-language model
excelling in free-form text-image composition and comprehension. This model
goes beyond conventional vision-language understanding, adeptly crafting
interleaved text-image content from diverse inputs like outlines, detailed
textual specifications, and reference images, enabling highly customizable
content creation. InternLM-XComposer2 proposes a Partial LoRA (PLoRA) approach
that applies additional LoRA parameters exclusively to image tokens to preserve
the integrity of pre-trained language knowledge, striking a balance between
precise vision understanding and text composition with literary talent.
Experimental results demonstrate the superiority of InternLM-XComposer2 based
on InternLM2-7B in producing high-quality long-text multi-modal content and its
exceptional vision-language understanding performance across various
benchmarks, where it not only significantly outperforms existing multimodal
models but also matches or even surpasses GPT-4V and Gemini Pro in certain
assessments. This highlights its remarkable proficiency in the realm of
multimodal understanding. The InternLM-XComposer2 model series with 7B
parameters are publicly available at
this https URL

InternLM-XComposer2 是一种先进的视觉 - 语言模型，擅长自由形式的文本 - 图像组合和理解，在从轮廓、详细的文本规范和参考图像等多样输入中巧妙地创建交错的文本 - 图像内容，实现了高度可定制的内容创作。InternLM-XComposer2 提出了 “Partial LoRA (PLoRA)” 方法，将额外的 LoRA 参数专门应用于图像标记，以保留预训练语言知识的完整性，在精确的视觉理解和具有文学才能的文本组合之间取得平衡。实验结果表明，在产生高质量的长文本多模态内容和在各种基准测试中的出色视觉 - 语言理解性能方面，InternLM-XComposer2 基于 InternLM2-7B 模型具有明显优势，不仅显著优于现有的多模态模型，而且在某些评估中甚至超过 GPT-4V 和 Gemini Pro，凸显了它在多模态理解领域的卓越能力。InternLM-XComposer2 系列模型的参数为 7B，可公开获取。

InternLM-XComposer2：掌握视觉语言大型模型中的自由文本 - 图像组合和理解

InternLM-XComposer2: Mastering Free-form Text-Image Composition and  Comprehension in Vision-Language Large Model

Neuron Interpretation has gained traction in the field of interpretability,
and have provided fine-grained insights into what a model learns and how
language knowledge is distributed amongst its different components. However,
the lack of evaluation benchmark and metrics have led to siloed progress within
these various methods, with very little work comparing them and highlighting
their strengths and weaknesses. The reason for this discrepancy is the
difficulty of creating ground truth datasets, for example, many neurons within
a given model may learn the same phenomena, and hence there may not be one
correct answer. Moreover, a learned phenomenon may spread across several
neurons that work together -- surfacing these to create a gold standard
challenging. In this work, we propose an evaluation framework that measures the
compatibility of a neuron analysis method with other methods. We hypothesize
that the more compatible a method is with the majority of the methods, the more
confident one can be about its performance. We systematically evaluate our
proposed framework and present a comparative analysis of a large set of neuron
interpretation methods. We make the evaluation framework available to the
community. It enables the evaluation of any new method using 20 concepts and
across three pre-trained models.The code is released at
this https URL

该研究提出了一种评估框架，用于比较不同神经元解释方法，通过该框架，可以评估任何新的神经元解释方法，通过与其他大多数方法的兼容性来评估其性能。