nlp-uoregon / okapi Goto Github PK

Issue Description:

I've encountered an issue while downloading the English language data. Specifically, the dataset appears to include only the 52K English instructions, omitting the multilingual-ranking-data-42k and multilingual-rl-tuning-64k datasets in English. Interestingly, these datasets are available in other languages.

I would appreciate guidance on where to access the missing English datasets. Your assistance in resolving this matter is highly valued.

Thank you.

I wanted to check if you trained RLHF models for English as well. If so, could you share those models as well?

Hi!
Thank you for your awesome work!
I had a few doubts:

• I understand you have finetuned on all languages separately: https://huggingface.co/uonlp. I was curious if you had attempted to finetune for all languages simultaneously for improved multi-lingual understanding. And if you had a single model which would work across all the high, medium and low resource languages.
• For the base LLM, you seem to have used BLOOM and LLama-7B on which you are applying an Instruction fine-tuning techniques (like Supervised fine-tuning (SFT)) on the 3 datasets - ARC, HellaSwag and MMLU. Did not use Llama-2-chat which is already fine-tuned via SFT for a bigger corpus of (instruction, input, output) pairs.

Please do let me know the same if there is a gap in my understanding! Thanks again

Vikrant Dewangan

I tried using git lfs pull to fetch the dataset, but it seems to have been deleted. Can you possibly share it on another storage location like huggingface datasets?