Abdelrahman Shaker

Hello, The number of FLOPs for input size of 96x96x96 is written in Table. 5. in UNETR paper as **_41.19 GFLOPS_**. However, I measured it using [ptflops ](https://github.com/sovrasov/flops-counter.pytorch) and it...

AMD support

1

Hi authors, Thank you for your awesome work. I have a question, please. Is qlora supports AMD GPUs? I don't have CUDA and I have errors regarding quantization "undefined symbol:...

Hi @carmocca , I have one issue regarding running the full fine-tuning using multi-node training. The code hangs during initializing deepspeed distributed after this output: `initializing deepspeed distributed: GLOBAL_RANK: 0,...

How to submit lightening model for evaluation

2

Hi, I have a question please, assume that I fine-tuned the Falcon model with adapters on a specific dataset and want to upload it on [openLLM leaderboard ](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)for evaluation. The...

### Branch main branch (1.x version, such as `v1.0.0`, or `dev-1.x` branch) ### Prerequisite - [X] I have searched [Issues](https://github.com/open-mmlab/mmaction2/issues) and [Discussions](https://github.com/open-mmlab/mmaction2/discussions) but cannot get the expected help. - [X]...

Hi, Thank you for sharing your work with the research community. I can't reproduce the CPU time of the EfficientFormer V1. I am using iPhone 14 pro max and following...

[Reproducing classification results of EfficientFormer_L1]

3

Hi, Thank you for sharing your research work. I am trying to reproduce the classification results of efficientformer_l1, I followed the instruction in your repo by running the following command:...

English-to-Arabic Translation Issue

1

Hi @Nagoudi @elmadany , Thank you so much for open-sourcing your awesome models. I have a question please, I want to use AraT5 or AraT5v2 for machine translation from English...

[ptb perplexity is different from paper]

9

Hi, Thank you for sharing your work. The re-produced perplexity for ptb dataset using your code is not matched with the paper. The reproduced is 27.8, while in the paper...

Evaluation code for Falcon models

1

Hi Authors, Thank you for sharing the evaluation code for llama models. Could you please release the code for the evaluation of Falcon models? Best regards, Abdelrahman.