Arabic RAG Leaderboard: A Comprehensive Framework for Evaluating Arabic Language Retrieval Systems
•
12
Navid AI
Enterprise
company
AI & ML interests
We are excited to announce our new organization account on Hugging Face, showcasing our leadership in advancing Arabic Large Language Models (LLMs). Our focus is on leveraging state-of-the-art pretraining, fine-tuning, and preference alignment techniques to empower organizations and individuals with personalized bilingual LLMs, significantly enhancing their capabilities and productivity.
Recent Activity
View all activity
Articles
Navid-AI's activity
MohamedRashad
updated
a
Space
12 days ago
MohamedRashad
updated
a
Space
14 days ago
MohamedRashad
posted
an
update
25 days ago
Post
2447
I collected the recitations of the holy quran from 20 different reciters and uploaded the full dataset here:
MohamedRashad/Quran-Recitations
Check it out 🥷
MohamedRashad/Quran-Recitations
Check it out 🥷
MohamedRashad
posted
an
update
about 1 month ago
Post
2106
For those interested in trying the new
canopylabs/orpheus-3b-0.1-ft model i made a space for you:
MohamedRashad/Orpheus-TTS
MohamedRashad/Orpheus-TTS
-
- 4 replies
MohamedRashad
posted
an
update
about 2 months ago
Post
3500
I think we have released the best Arabic model under 25B at least based on https://huggingface.co/spaces/inceptionai/AraGen-Leaderboard
Yehia = 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:
Navid-AI/Yehia-7B-preview
or Download it for your personal experiments from here:
Navid-AI/Yehia-7B-preview
Ramadan Kareem 🌙
Yehia = 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:
Navid-AI/Yehia-7B-preview
or Download it for your personal experiments from here:
Navid-AI/Yehia-7B-preview
Ramadan Kareem 🌙
- 1 reply
MohamedRashad
posted
an
update
2 months ago
Post
3320
Today is a big day for the Arabic Language,
We have Navid-AI/The-Arabic-Rag-Leaderboard,
an Update for OALL/Open-Arabic-LLM-Leaderboard
and the release of atlasia/darija-chatbot-arena
All of this announcements was under 12 hours of time 🤯
We have Navid-AI/The-Arabic-Rag-Leaderboard,
an Update for OALL/Open-Arabic-LLM-Leaderboard
and the release of atlasia/darija-chatbot-arena
All of this announcements was under 12 hours of time 🤯
MohamedRashad
posted
an
update
4 months ago
Post
2087
The winners of Best Paper Award in NeurIPs2024 (FoundationVision)
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale
Prediction (2404.02905) has just released a new paper called infinty:
Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis (2412.04431)
And i managed to build a space for it so anyone can try it out: MohamedRashad/Infinity
The idea of a text to image model using autoregressive archticture is quite interesting in my opinion.
Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis (2412.04431)
And i managed to build a space for it so anyone can try it out: MohamedRashad/Infinity
The idea of a text to image model using autoregressive archticture is quite interesting in my opinion.
MohamedRashad
posted
an
update
4 months ago
Post
2817
For those Game Developers out there who wants a tool to generate them 3d assets of different game items. I built something for you 😅
JeffreyXiang/TRELLIS-image-large +
Qwen/Qwen2.5-72B-Instruct +
Freepik/flux.1-lite-8B-alpha =
MohamedRashad/Game-Items-Generator
Happy building 🎉
JeffreyXiang/TRELLIS-image-large +
Qwen/Qwen2.5-72B-Instruct +
Freepik/flux.1-lite-8B-alpha =
MohamedRashad/Game-Items-Generator
Happy building 🎉
- 1 reply
MohamedRashad
posted
an
update
5 months ago
Post
1704
A while back i shared this model
MohamedRashad/arabic-small-nougat that was a finetune from
facebook/nougat-small for the Arabic Language.
Today this humble project has been scaled with new models, new datasets, new space, and a new paper
Check everything throught this collection here:
MohamedRashad/arabic-nougat-673a3f540bd92904c9b92a8e
Today this humble project has been scaled with new models, new datasets, new space, and a new paper
Check everything throught this collection here:
MohamedRashad/arabic-nougat-673a3f540bd92904c9b92a8e
- 1 reply
MohamedRashad
posted
an
update
5 months ago
Post
436
For those who want to try out the new
black-forest-labs/FLUX.1-Redux-dev
You can do this from my latest spaces MohamedRashad/Flux-Redux
You can do this from my latest spaces MohamedRashad/Flux-Redux
MohamedRashad
posted
an
update
7 months ago
Post
1024
Qwen2.5-72B + Flux-dev + FinePersonas = Grounded Structured Character Generator
Check out my latest projects that uses Qwen/Qwen2.5-72B-Instruct , black-forest-labs/FLUX.1-dev , and MohamedRashad/FinePersonas-Lite to generate different characters in a world of your description.
Try Here: MohamedRashad/Character-Generator 🤗
Check out my latest projects that uses Qwen/Qwen2.5-72B-Instruct , black-forest-labs/FLUX.1-dev , and MohamedRashad/FinePersonas-Lite to generate different characters in a world of your description.
Try Here: MohamedRashad/Character-Generator 🤗
MohamedRashad
posted
an
update
7 months ago
Post
3500
For all the Muslims out there who are interested in Quran and its tafsir (explanations). This humble dataset consists of 84 different books of tafsir for nearly all the ayat in the Quran:
MohamedRashad/Quran-Tafseer
I hope it helps someone to build something nice and useful with it ^_^
MohamedRashad/Quran-Tafseer
I hope it helps someone to build something nice and useful with it ^_^
MohamedRashad
posted
an
update
10 months ago
Post
2608
Check
@lllyasviel
Latest research for making videos of still images using hand drawing keyframes:
https://lllyasviel.github.io/pages/paints_undo/
I imported his work to gradio space here
MohamedRashad/PaintsUndo
https://lllyasviel.github.io/pages/paints_undo/
I imported his work to gradio space here
MohamedRashad/PaintsUndo
MohamedRashad
posted
an
update
10 months ago
Post
2173
Yet Another Whisper Finetune
MohamedRashad/Arabic-Whisper-CodeSwitching-Edition is a finetune of OpenAI Whisper Large V2 on MohamedRashad/arabic-english-code-switching dataset.
This new finetune is capable of recognizing english words in arabic speech and transcribing the foreign words as it is.
Try it out here:
MohamedRashad/Arabic-Whisper-CodeSwitching-Edition
MohamedRashad/Arabic-Whisper-CodeSwitching-Edition is a finetune of OpenAI Whisper Large V2 on MohamedRashad/arabic-english-code-switching dataset.
This new finetune is capable of recognizing english words in arabic speech and transcribing the foreign words as it is.
Try it out here:
MohamedRashad/Arabic-Whisper-CodeSwitching-Edition
MohamedRashad
posted
an
update
10 months ago
Post
813
Just updated
MohamedRashad/timm-leaderboard with fuzzy search for people who want to search for a certian vision model
MohamedRashad
posted
an
update
11 months ago
Post
1546
Timm Leaderboard space here:
MohamedRashad/timm-leaderboard
Thanks goes to @rwightman for building timm 🤗
MohamedRashad/timm-leaderboard
Thanks goes to @rwightman for building timm 🤗
MohamedRashad
posted
an
update
11 months ago
Post
1224
@Ali-C137
and the team at OALL Just released
OALL/Open-Arabic-LLM-Leaderboard
Amazing effort to push the Arabic LLMs development forward 👏
Amazing effort to push the Arabic LLMs development forward 👏
MohamedRashad
posted
an
update
12 months ago
Post
1878
For those who love the Arabic language like me, This is a summary of my different models, datasets and spaces i made the last couple of months:
1. MohamedRashad/Arabic-Orpo-Llama-3-8B-Instruct is a finetuned version of Meta-Llama-3-8B-Instruct using ORPO on 2A2I/argilla-dpo-mix-7k-arabic and the space to try it is here MohamedRashad/Arabic-Chatbot-Arena.
2. MohamedRashad/arabic-small-nougat is a finetuned version of facebook/nougat-small on Arabic book pages to be a capable arabic-ocr and its space is also avialable here https://huggingface.co/spaces/MohamedRashad/Arabic-Small-Nougat.
3. There is MohamedRashad/Arabic-CivitAi-Images dataset for text-to-image in the Arabic language (Hope someone utilize it to build something great).
4. MohamedRashad/arabic-sts for those who want to train an Arabic Text Embedder model.
5. Finally, a small arabic dataset about translation from Fusha Arabic to English called MohamedRashad/rasaif-translations (This dataset is very important in my opinion).
1. MohamedRashad/Arabic-Orpo-Llama-3-8B-Instruct is a finetuned version of Meta-Llama-3-8B-Instruct using ORPO on 2A2I/argilla-dpo-mix-7k-arabic and the space to try it is here MohamedRashad/Arabic-Chatbot-Arena.
2. MohamedRashad/arabic-small-nougat is a finetuned version of facebook/nougat-small on Arabic book pages to be a capable arabic-ocr and its space is also avialable here https://huggingface.co/spaces/MohamedRashad/Arabic-Small-Nougat.
3. There is MohamedRashad/Arabic-CivitAi-Images dataset for text-to-image in the Arabic language (Hope someone utilize it to build something great).
4. MohamedRashad/arabic-sts for those who want to train an Arabic Text Embedder model.
5. Finally, a small arabic dataset about translation from Fusha Arabic to English called MohamedRashad/rasaif-translations (This dataset is very important in my opinion).
-
- 2 replies
MohamedRashad
posted
an
update
12 months ago
