beyondguo

init.lua:235: Not a JPEG file: starts with 0x47 0x49

1

I have more than 10000 pictures to caption. It successfully captioned 1000 pictures and then I got this error: ``` /root/torch/install/bin/luajit: /root/torch/install/share/lua/5.1/image/init.lua:235: Not a JPEG file: starts with 0x47 0x49...

How to assign new values to Dataset?

1

 Hi, if I want to change some values of the dataset, or add new columns to it, how can I do it? For example, I want to change all...

## 描述 在Mac M1上无法安装。  ## 功能 ## 操作系统 - [ √] macOS or Mac OSX - [ ] Windows - [ ] Linux(Debian, CentOS, Ubuntu, etc.) ## 代码版本 ##...

Hi Jason! Sorry to interrupt you. I can't contact you via email. I have to try this place. I am very interested in your EMNLP paper "**Good-Enough Example Extrapolation**", which...

How to generate more than 1 augmented samples using Back-Translation method?

1

How to generate more than 1 augmented samples using Back-Translation method? Current implementation of `BackTranslationAug` can only support generating a single text, but actually we can change the decoding strategy...

Unable to augment Chinese, given corresponding language model.

3

Using Context-word-enbedding augmenter: English: ```python text = 'hi how are you' context_aug = naw.ContextualWordEmbsAug( model_path='bert-base-uncased', action="substitute") augmented_text = context_aug.augment(text) print("Original:") print(text) print("Augmented Text:") print(augmented_text) ``` output is ok: ``` Original:...

It there going to be a platform so I can evaluate my method on it?

关于evaluate函数中loss计算是否准确的问题？

1

作者你好！非常感谢你的代码，清晰明了。有一个小细节想讨论一下： 在根据loss判断模型是否更好的时候，会通过evaluate函数计算loss： ```python def evaluate(config, model, data_iter, test=False): model.eval() loss_total = 0 predict_all = np.array([], dtype=int) labels_all = np.array([], dtype=int) with torch.no_grad(): for texts, labels in data_iter: outputs = model(texts)...

[Question] 2行代码开启baichuan-7B的LoRA微调

17

### Required prerequisites - [X] I have read the documentation . - [X] I have searched the [Issue Tracker](https://github.com/baichuan-inc/baichuan-7B/issues) and [Discussions](https://github.com/baichuan-inc/baichuan-7B/discussions) that this hasn't already been reported. (+1 or comment...