mathav95raj

It is addressed in the paper in the introduction . Language models learnt in traditional maximum likelihood approach suffer exposure bias. Though there are techniques like scheduled sampling to overcome...

Yes I did solve the issue by going for sklearn but from the pypi link I had posted, it can be seen that the scikit learn commuity is recommending to...

What was your hardware spec? Did you try with the fine tuning script in the repo?

Hello all, any updates on this?

Hi all, wil there be an update on including `llama-gemma3-cli` in the application since it enables vision support in Gemma 3 as per https://github.com/ggml-org/llama.cpp/pull/12344

@Djip007 My bad. I had done the above tests with latest release v0.8.13 but while filling the github issue, I mentioned the version from the issue default template. I apologise...

able to get correct results now. Thanks!