John Locke
johnlockejrr
AI & ML interests
NLP, OCR, AI
Recent Activity
reacted
to
MohamedRashad's
post
with ❤️
10 days ago
I think we have released the best Arabic model under 25B at least based on https://huggingface.co/spaces/inceptionai/AraGen-Leaderboard
Yehia = https://huggingface.co/ALLaM-AI/ALLaM-7B-Instruct-preview + GRPO
and its ranked number one model under the 25B parameter size mark.
Now, i said "i think" not "i am sure" because this model used the same metric of evaluation the AraGen developers use (the 3C3H) as a reward model to improve its responses and this sparks the question. Is this something good for users or is it another type of overfitting that we don't want ?
I don't know if this is a good thing or a bad thing but what i know is that you can try it from here:
https://huggingface.co/spaces/Navid-AI/Yehia-7B-preview
or Download it for your personal experiments from here:
https://huggingface.co/Navid-AI/Yehia-7B-preview
Ramadan Kareem 🌙
liked
a Space
13 days ago
Navid-AI/Yehia-7B-preview
Organizations
None yet
johnlockejrr's activity
PyLaia enhancement
2
#7 opened about 2 months ago
by
johnlockejrr
New activity in
cantillation/Teamim-small_Random_WeightDecay-0.05_Augmented_New-Data_date-02-08-2024
2 months ago
A little info
#1 opened 2 months ago
by
johnlockejrr
Model inference
1
#1 opened 3 months ago
by
johnlockejrr
Arabic Small Nougat
10
#1 opened 11 months ago
by
johnlockejrr
Finetune the model on other writing systems like Arabic or Hebrew
1
#1 opened 4 months ago
by
johnlockejrr
How to predict
2
#1 opened 5 months ago
by
johnlockejrr
Neue Materialien zum aramäischen Dialekt von Ma'lula
9
#1 opened 5 months ago
by
johnlockejrr
what preprocessor should I use to train the handwritten arabic ocr on this base of ArOCR model?
2
#1 opened over 2 years ago
by
HGamal
How to interfere with this model?
#2 opened 5 months ago
by
johnlockejrr
OSError: UBC-NLP/Qalam is not a local folder
#1 opened 5 months ago
by
johnlockejrr
surya-ocr-arabic-segment tune script
#1 opened 6 months ago
by
johnlockejrr
Convert polygons to YOLOv8 masks
1
#3 opened 6 months ago
by
johnlockejrr
Teklia/doc-ufcn-generic-historical-line train
2
#6 opened 9 months ago
by
johnlockejrr
Librarian Bot: Add language metadata for dataset
#2 opened 11 months ago
by
librarian-bot

All translations won't make sense
#3 opened 11 months ago
by
johnlockejrr
Librarian Bot: Add language metadata for dataset
#1 opened 11 months ago
by
librarian-bot

[bot] Conversion to Parquet
#1 opened 11 months ago
by
parquet-converter

!חג שמח
3
#1 opened 11 months ago
by
johnlockejrr
Fine-tuning BEREL_2.0 for Samaritan Hebrew (Torah) and Samaritan Aramaic
#2 opened 11 months ago
by
johnlockejrr