ckq
ckq
> hi could rephrase your questions? chongkuiqi 于 2021年2月23日周二 10:50写道： > […](#) > Thanks for your code ! When i use imitation loss in my dataset and work, i'm confused...
> for custom data, I suggest you first keep the two-loss at similar level, then tune the imitation loss. chongkuiqi 于 2021年2月23日周二 17:32写道： > […](#) > hi could rephrase your...
> we did not examine the choice of adaptation kernel size, you can try tune if on you data. > […](#) > On Thu, Feb 25, 2021 at 11:24 AM...
> I guess the reason is: cuda11.0 requires higher version pytorch (>1.3), while some [ops](https://github.com/csuhan/ReDet/tree/master/mmdet/ops) in our code are designed for pytorch > If so, to fix this, you need...
> > > I guess the reason is: cuda11.0 requires higher version pytorch (>1.3), while some [ops](https://github.com/csuhan/ReDet/tree/master/mmdet/ops) in our code are designed for pytorch > > If so, to fix...
> It is the question of ip address for me. Setting the proxy of the terminal works: `export https_proxy=http://127.0.0.1:%Port%;export http_proxy=http://127.0.0.1:%Port%;export all_proxy=socks5://127.0.0.1:%Port%` Thanks, it works for me !
> The error `CUDA_ERROR_NO_BINARY_FOR_GPU` is likely ude to a mismatch of the cuda arch, you can try specifying the arch in the target Thanks for reply！But when I specifying the...
> @chongkuiqi could you please share the build files generated after running `prepare_libs.sh` for Llama3? Let me try. I didn't use prepare_libs.sh, I just use mlc_llm compile ./dist/Llama-3-8B-Instruct-q4f16_1-MLC/mlc-chat-config.json ... to...