Merlin
Merlin
> Hello,glad to see your excellent work.I wonder whether you can supply the results at commom datasets like coco or voc? thx for replying. With this code, the experiment at...
> I use the same config files to execute Probablistic Teacher on KITTI to Cityscapes (k2c). According to your paper, AP of k2c improve from 40.3 to 60.2. However, I...
> Hello, we will update in this month.
> The pre-training losses are always negative (like -199.03), is that normal? I got the negative loss also, have you solve it?
hello，in my understanding，fauxpilot uses the gptj inerface in triton ft backend due to codegen shares the same arch with gptj. If i want to add a model that has slightly...
也就是非 streaming 模式会 shuffle 整个训练数据集，streaming 模式只是在sample data 时候会在buffersize内进行 shuffle？
I met the same issue. Have you find a solution? @Luoyang144
While weight conversion of llama-13b getting this error: RuntimeError: Internal: unk is not defined.
> I am using linux ubunto. > > with following virtual environment > > **accelerate==0.18.0 certifi==2022.12.7 charset-normalizer==3.1.0 cmake==3.26.3 filelock==3.12.0 huggingface-hub==0.13.4 idna==3.4 Jinja2==3.1.2 lit==16.0.1 MarkupSafe==2.1.2 mpmath==1.3.0 networkx==3.1 numpy==1.24.2 nvidia-cublas-cu11==11.10.3.66 nvidia-cuda-cupti-cu11==11.7.101 nvidia-cuda-nvrtc-cu11==11.7.99...
> ### Describe the feature > [OpenAI/evals](https://github.com/openai/evals/tree/main/evals/registry/data) contains many community-sourced tasks, with about 400-500 datasets covering various languages and fields. Compared to other open-source datasets, they have very few questions,...
Same issue, has anybody solved this ?