文件最后提交记录最后更新时间
[feature] add MiMoV2.5 model Co-authored-by: ghoshaw<chenzhiguo6@huawei.com> # message auto-generated for no-merge-commit merge: !2448 merge master into master [feature] add MiMoV2.5 model Created-by: ghoshaw Commit-by: ghoshaw Merged-by: ascend-robot Description: ## What this PR does / why we need it? 增加 MiMoV2.5 模型支持。 这个是原仓合入的代码,所以代码量比较大。 ## Does this PR introduce any user-facing change? 无 ## How was this patch tested? 在NPU 上减层(2 层)加载qwen2vl 数据集跑通功能,loss收敛. 未测试语音输入 。测试时视觉部分和语音部分均冻结。 开源权重为量化版,功能跑通使用随机初始化权重。 See merge request: Ascend/MindSpeed-MM!244826 天前
[feature] add script and ut for mimov25 Co-authored-by: ghoshaw<chenzhiguo6@huawei.com> # message auto-generated for no-merge-commit merge: !2477 merge master into master [feature] add script and ut for mimov25 Created-by: ghoshaw Commit-by: ghoshaw Merged-by: ascend-robot Description: ## What this PR does / why we need it? 增加MiMo V2.5 的运行脚本和UT用例。 ## Does this PR introduce any user-facing change? 无 ## How was this patch tested? 单机减层验证功能OK, 未加载模型权重。 See merge request: Ascend/MindSpeed-MM!247712 天前