9bbefa2d创建于 3月10日历史提交

文件	最后提交记录	最后更新时间
pretrain_llava.sh	!2284 fix: Adapt to core0.10.0; v2 is aligned with v1 Merge pull request !2284 from 邓佳/master_te	1 年前
readme.md	doc: adjust doc Co-authored-by: liutongtong27<liutongtong15@h-partners.com> # message auto-generated for no-merge-commit merge: !3305 merge master_menutest into master doc: adjust doc Created-by: liutongtong27 Commit-by: liutongtong27 Merged-by: ascend-robot Description: What this PR does / why we need it? Please describe the background and detailed changes of the PR. If it is a bugfix, please attach the related issue. Does this PR introduce any user-facing change? Please describe whether the PR will result in any user-facing usage changes. If there is related documentation, please specify its path. How was this patch tested? Please explain how to verify the correctness and effectiveness of this feature, as well as its usage constraints and limitations. See merge request: Ascend/MindSpeed!3305	2 个月前

背景

作为一种能够处理和理解多种模态数据（如文本、图像、声音等）的人工智能模型，LLAVA系列多模态大模型具有强大的表现力和广泛的应用前景。Megatron官方仓早在060版本便发布llava大模型入口pretrain_vlm.py文件，Mindspeed也需不断做出适配。

操作步骤

cd Megatron-LM/
ls -n ../MindSpeed/mindSpeed ./mindSpeed
cp ../MindSpeed/tests_extend/llava/pretrain_llava.sh ./pretrain_llava.sh
bash pretrain_llava.sh