Nathan Cooper

Hi @gadnyz could you add some additional information? Specifically, what version of Jupyter and python you are using, could you also provide the additional context of code to reproduce your...

Retro is now officially supported in megatron! https://github.com/NVIDIA/Megatron-LM#retro I'm new to the neox/megatron codebase, but if someone is willing to discuss some advice/suggestions on how to get started with this...

HI there, could you share some more info. Specifically, what version of vscode you are using, the command you ran to recompile and the full stack trace?

I also am experiencing this

I'm getting a similar issue even though I've already downloaded the dataset 😅 ``` huggingface_hub.utils._errors.HfHubHTTPError: 429 Client Error: Too Many Requests for url: https://huggingface.co/api/datasets/HuggingFaceM4/WebSight ```

Is there any easy way to just add a git repo to be installed in the settings.ini requirements var? Naively adding the git+https://... to requirements var produces the following error:...

Facing similar issue

@virattt Glad it was helpful!

@monisha08041998 It was only trained on a max length of 9 conversations, so going beyond that may leads to poor results. Also, the max length of the entire conversation that...

@bhuvan1643 DialoGPT used the original GPT2 model, pretrained weights, and tokenizer. Even though the vast majority of the data was English, it still contained some Spanish text and therefore the...