open_llama

open_llama copied to clipboard

Hi, I made a YouTube video on how to run OpenLLaMa on Google Colab with Transformers. I am adding it to a resources section along with a link to a...

curiousily

Hi, I finetuned the 300bt checkpoint with alpaca+sharegpt but while with llama code generation works fine with openllama the backticks are missing around code blocks. did you eliminate those in...

vince62s

Huggingface -> Hugging Face

eltociear

Thanks! Does it fit in Free Colab?

3

Hey Thanks very much for the effort. Looking at the released model size, Wondering if it can fit in Free Colab?

amrrs

Add larger-than-character-level subword vocab for non-latin languages?

2

Hi OpenLM team, Thank for such great contribution to the open source community. At [PythaiNLP](https://github.com/PyThaiNLP/WangChanGLM) we've been trying to replicate Alpaca-like instruction followers for non-latin languages (Thai, Japanese, Vietnamese and...

cstorm125

Any plans to train for 30b model

5

Are there any plans to train a 30b replica of Llama or is the 7b enough to meet your purposes of comparison?

mtc2013

Excellent work. For the checkpoint at 300B tokens, would you mind sharing the lm-evaluation-harness metrics?

enijkamp

Why is this better than llama in some instances?

1

I was going through the readme and noticed [here](https://github.com/openlm-research/open_llama#evaluation) that this model is performing better than the 7B llama on many things, even though its trained on a fifth of...

rick2047

First of all, I would like to express my gratitude for making this available on such a permissive license, it opens new doors to both researchers and industries. 1) Could...

maximegmd

Corpora for Ukrainian

1

Hello. There is a corpora call Ubercorpus for Ukrainian you can add to the project: https://lang.org.ua/en/corpora/#anchor4 In a few days will be UNLP, an event from Ukrianian NLP community and...

egorsmkv