APiaoG

Thank you for your outstanding work! Recently, I have been trying to test the performance of GPT-3.5 turbo on gsm8k, but I have received poor results, as shown in the...

eval_loss结果与原文结果不一致

3

您好！我在复现论文eval_loss的结果时发现评估结果不一致，我想问一下这是正常的吗？ 以下是原文结果  我自己复现的结果如下： 

NAN value when using the pre-trained model

2

Hello! Great works! What is the reason why I encountered a nan value when using the pre trained model? Looking forward to your reply! 

Train data

1

您好，感谢您的开源和杰出的工作！我想问一下在SEED/MultiModalLLM/configs/data/caption_torchdata_preprocess.yaml中 data_dir: - ${oc.env:PROJECT_ROOT}/data/unsplash_resize/webdataset - CC3M/webdataset/gcc3m_shards 我想问一下这里的数据集从哪里下载呢？我关注到论文里有说“We filtered the samples in these datasets based on image resolution, aspect ratio, and visual-textual similarity. We randomly place images or text at the...

如何获取训练数据？

1

您好！非常感谢您的杰出的开源工作！我想问一下以下训练数据可否可以开源呢？ data_dir: - dataset/seed_v2_0828/caption/unsplash_cc3m - dataset/seed_v2_0828/caption/coco data_dir: /dataset/seed_v2_0828/caption/laion-coco data_dir: dataset/seed_v2_0828/image_interleaved/mmc4 data_dir: dataset/seed_v2_0828/image_interleaved/obelisc data_dir: dataset/seed_v2_0828/caption/WebVid-10m data_dir: dataset/wikipedia_20220301.en 或者是经过src/tools/extract_image_ids_to_torchdata_parallel.py 预处理之前的数据集可否提供一下呢？非常感谢！

Hello! Great Work! But can you write down the configuration file (Readme.md) in detail? I am not very clear about the environmental requirements, dataset location requirements, and how to use...