Mohamed Hesham Abdalla

Execution failed for task ':react-native-unity-view:compileDebugJavaWithJavac'.

4

` FAILURE: Build failed with an exception. * What went wrong: Execution failed for task ':react-native-unity-view:compileDebugJavaWithJavac'. > Compilation failed; see the compiler error output for details. * Try: Run with...

pad token as eos token for gpt2 classification

1

Hello, First of all thanks a lot for the tutorials! I have a question regarding the pad token. In the GPT-2 for classification example, you set padding to be the...

support for older models

1

Hello, I was wondering if it is straightforward to bring older models such as GPT-2 to lit-gpt. If so, what files/configs do I need to change? Thank you!

[BUG] using gpt2 model results in nan metrics and !!! output

2

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

[Question] EOS in reward model dataset

4

Hi, first of all thank you very much for the repo! I would like to ask, is the EOS token in the reward model dataset necessary for the model? I'm...

[Bug Report] loading gemma-7b-it runs out of memory

2

**Describe the bug** When loading gemma-7b-it on a machine with 2 H100, the loading still fails on a jupyter notebook. **Code example** ``` n_devices=2 model = HookedTransformer.from_pretrained_no_processing( "google/gemma-7b-it", center_writing_weights=False, fold_value_biases=False,...