2
Yehia 7B Preview
π¬
Good Arabic Model
Mohamed Rashad PRO
MohamedRashad
AI & ML interests
Computer Vision, Robotics, Natural Language Processing
Recent Activity
updated
a Space
about 2 hours ago
Navid-AI/Yehia-7B-preview
liked
a Space
about 4 hours ago
Navid-AI/Yehia-7B-preview
liked
a dataset
1 day ago
halabi2016/arabic_speech_corpus
Organizations
MohamedRashad's activity
updated
a
Space
about 2 hours ago
liked
a
Space
about 4 hours ago
liked
a
dataset
1 day ago
Flux-Redux Paused Status
3
#1 opened 6 days ago
by
Resoldjew
Fixes 500 error for some users
1
#1 opened 6 days ago
by
Tonic
updated
a
Space
6 days ago
liked
a
Space
6 days ago
Adding Arabert
2
#3 opened 9 days ago
by
wissamantoun
liked
a
model
7 days ago
liked
a
Space
15 days ago
Can't see reranking submission
3
#1 opened 18 days ago
by
anondeb
reacted to
their
post with π₯
18 days ago
Post
3274
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 π€―
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 π€―
posted
an
update
18 days ago
Post
3274
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 π€―
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 π€―
reacted to
lewtun's
post with β€οΈ
18 days ago
Post
4599
Introducing OpenR1-Math-220k!
open-r1/OpenR1-Math-220k
The community has been busy distilling DeepSeek-R1 from inference providers, but we decided to have a go at doing it ourselves from scratch πͺ
Whatβs new compared to existing reasoning datasets?
βΎ Based on AI-MO/NuminaMath-1.5: we focus on math reasoning traces and generate answers for problems in NuminaMath 1.5, an improved version of the popular NuminaMath-CoT dataset.
π³ 800k R1 reasoning traces: We generate two answers for 400k problems using DeepSeek R1. The filtered dataset contains 220k problems with correct reasoning traces.
π 512 H100s running locally: Instead of relying on an API, we leverage vLLM and SGLang to run generations locally on our science cluster, generating 180k reasoning traces per day.
β³ Automated filtering: We apply Math Verify to only retain problems with at least one correct answer. We also leverage Llama3.3-70B-Instruct as a judge to retrieve more correct examples (e.g for cases with malformed answers that canβt be verified with a rules-based parser)
π We match the performance of DeepSeek-Distill-Qwen-7B by finetuning Qwen-7B-Math-Instruct on our dataset.
π Read our blog post for all the nitty gritty details: https://huggingface.co./blog/open-r1/update-2
open-r1/OpenR1-Math-220k
The community has been busy distilling DeepSeek-R1 from inference providers, but we decided to have a go at doing it ourselves from scratch πͺ
Whatβs new compared to existing reasoning datasets?
βΎ Based on AI-MO/NuminaMath-1.5: we focus on math reasoning traces and generate answers for problems in NuminaMath 1.5, an improved version of the popular NuminaMath-CoT dataset.
π³ 800k R1 reasoning traces: We generate two answers for 400k problems using DeepSeek R1. The filtered dataset contains 220k problems with correct reasoning traces.
π 512 H100s running locally: Instead of relying on an API, we leverage vLLM and SGLang to run generations locally on our science cluster, generating 180k reasoning traces per day.
β³ Automated filtering: We apply Math Verify to only retain problems with at least one correct answer. We also leverage Llama3.3-70B-Instruct as a judge to retrieve more correct examples (e.g for cases with malformed answers that canβt be verified with a rules-based parser)
π We match the performance of DeepSeek-Distill-Qwen-7B by finetuning Qwen-7B-Math-Instruct on our dataset.
π Read our blog post for all the nitty gritty details: https://huggingface.co./blog/open-r1/update-2
upvoted
an
article
18 days ago
Article
Arabic RAG Leaderboard: A Comprehensive Framework for Evaluating Arabic Language Retrieval Systems
By
and 1 other
β’
β’
11
updated
a
Space
19 days ago
liked
a
Space
19 days ago
published
an
article
19 days ago
Article
Arabic RAG Leaderboard: A Comprehensive Framework for Evaluating Arabic Language Retrieval Systems
By
and 1 other
β’
β’
11
published
an
article
19 days ago
Article
Arabic RAG Leaderboard: A Comprehensive Framework for Evaluating Arabic Language Retrieval Systems
By
and 1 other
β’
β’
11
updated
a
Space
19 days ago