文件最后提交记录最后更新时间
[docs]增加internvl3_5资料 Co-authored-by: 李明宇<limingyu35@h-partners.com> # message auto-generated for no-merge-commit merge: !490 merge master-internvl-dense-md into master [docs]增加internvl3_5资料 Created-by: code_mingming Commit-by: 李明宇 Merged-by: ascend-robot Description: 感谢您贡献的Pull Request! 在提交之前,请务必阅读 [CONTRIBUTING.md](https://gitcode.com/Ascend/msmodelslim/blob/master/CONTRIBUTING.md)。 Thanks for sending a pull request! BEFORE SUBMITTING, PLEASE READ [CONTRIBUTING.md](https://gitcode.com/Ascend/msmodelslim/blob/master/CONTRIBUTING.md). ## PR描述 (What this PR does / why we need it?) 增加internvl3_5资料 example/multimodal_vlm/README.md内的模型Readme.md资料链接统一加上书名号 ## 面向用户的变更 (Does this PR introduce _any_ user-facing change)? - 请注意,这里指的是**任何**面向用户的变更,包括但不限于API、用户界面或其他使用方式上的变更。 - Note that it means *any* user-facing change including all aspects such as API, interface or other behavior changes. ## 功能验证 (How was this patch tested?) 请确认CI已通过增量及存量的单元测试用例。 如果本次测试方式与常规单元测试不同,请详细说明您的测试步骤(最好提供完整的可复现的操作路径及关键截图),以便Committer能够快速复现验证,也便于后续的维护。 如果未添加测试,请说明未添加的原因,以及为何难添加测试。 - [_] 功能自验 - [_] 本地自验截图(涉及个人标识符等敏感信息请注意脱敏) - [_] 新增/变更内容是否已新增/适配UT测试用例看护 CI passed with new added/existing test. If it was tested in a way different from regular unit tests, please clarify how you tested step by step, ideally copy and paste-able, so that other reviewers can test and check, and descendants can verify in the future. If tests were not added, please describe why they were not added and/or why it was difficult to add. - [_] Self-verification of the feature. - [_] Screenshot of local self-verification (please anonymize any sensitive information such as personal identifiers) - [_] Have new or modified unit test (UT) cases been added or adapted to cover the newly added or changed content? See merge request: Ascend/msmodelslim!49017 小时前
README.md

InternVL 3.5 量化说明

模型介绍

  • InternVL 3.5 是由上海人工智能实验室推出的多模态大模型书生·万象系列的最新版本。通过级联式强化学习(Cascade RL)、视觉分辨率路由器(ViR)与解耦视觉语言部署(DvD)等创新,InternVL 3.5在推理能力、部署效率与通用能力上实现了全面升级,支持图形用户界面(GUI)智能体、具身智能体、矢量图像理解与生成等新颖功能。

使用前准备

InternVL 3.5模型当前已验证的量化方法

模型 原始浮点权重 量化方式 推理框架支持情况 量化命令
InternVL3_5-38B InternVL3_5-38B W8A8量化 vLLM Ascend W8A8量化

Note

  • 点击量化命令列中的链接可跳转到对应的具体量化命令。

使用示例

InternVL3_5-38B W8A8量化

该模型的量化已集成至一键量化,示例参数详见文档《一键量化完整指南》中的“参数说明”章节。

msmodelslim quant \
    --model_path {model_path} \
    --save_path {save_path} \
    --device npu \
    --model_type InternVL3_5-38B \
    --quant_type w8a8 \
    --trust_remote_code True

附录

相关资源