Post
1630
I think we just got the best Image to Markdown VLM out there and it's hosted here:
MohamedRashad/Nanonets-OCR
MohamedRashad/Nanonets-OCR
Mohamed Rashad PRO
MohamedRashad
AI & ML interests
Computer Vision, Robotics, Natural Language Processing
Recent Activity
updated
a Space
3 days ago
MohamedRashad/Character-Generator
updated
a Space
4 days ago
Navid-AI/The-Arabic-Rag-Leaderboard
Organizations
posted
an
update
19 days ago
reacted to
their
post with 👍
26 days ago
Post
327
I just updated an old (non working) space i had with the implementation of a cool research paper named UniRig
The idea is that you upload any 3d model and it rigs it for you with correct armature and the skinning process to give you the final model fully rigged and ready to be used.
Check it out here:
MohamedRashad/UniRig
The idea is that you upload any 3d model and it rigs it for you with correct armature and the skinning process to give you the final model fully rigged and ready to be used.
Check it out here:
MohamedRashad/UniRig
posted
an
update
28 days ago
Post
327
I just updated an old (non working) space i had with the implementation of a cool research paper named UniRig
The idea is that you upload any 3d model and it rigs it for you with correct armature and the skinning process to give you the final model fully rigged and ready to be used.
Check it out here:
MohamedRashad/UniRig
The idea is that you upload any 3d model and it rigs it for you with correct armature and the skinning process to give you the final model fully rigged and ready to be used.
Check it out here:
MohamedRashad/UniRig
posted
an
update
about 2 months ago
Post
1054
I have processed and cleaned the famous SADA2022 dataset from SADIA for Arabic ASR and other related tasks and uploaded it here:
MohamedRashad/SADA22
Edit:
I also added another dataset from SADIA named SCC22
MohamedRashad/SCC22
MohamedRashad/SADA22
Edit:
I also added another dataset from SADIA named SCC22
MohamedRashad/SCC22
replied to
their
post
3 months ago
Speech data in audio and text format
replied to
their
post
3 months ago
Start with gathering high quality data first. This is by far the biggest hurdle against TTS systems out there.
posted
an
update
3 months ago
Post
2693
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 🥷
- 1 reply
reacted to
their
post with 👀
3 months ago
Post
2128
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
posted
an
update
3 months ago
Post
2128
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
reacted to
their
post with ❤️
4 months ago
Post
3514
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
posted
an
update
4 months ago
Post
3514
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
reacted to
their
post with 🔥
5 months ago
Post
3329
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 🤯
posted
an
update
5 months ago
Post
3329
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 🤯
reacted to
lewtun's
post with ❤️
5 months ago
Post
5309
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 💪
What’s new compared to existing reasoning datasets?
♾ 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.
🐳 800k R1 reasoning traces: We generate two answers for 400k problems using DeepSeek R1. The filtered dataset contains 220k problems with correct reasoning traces.
📀 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.
⏳ 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 can’t be verified with a rules-based parser)
📊 We match the performance of DeepSeek-Distill-Qwen-7B by finetuning Qwen-7B-Math-Instruct on our dataset.
🔎 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 💪
What’s new compared to existing reasoning datasets?
♾ 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.
🐳 800k R1 reasoning traces: We generate two answers for 400k problems using DeepSeek R1. The filtered dataset contains 220k problems with correct reasoning traces.
📀 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.
⏳ 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 can’t be verified with a rules-based parser)
📊 We match the performance of DeepSeek-Distill-Qwen-7B by finetuning Qwen-7B-Math-Instruct on our dataset.
🔎 Read our blog post for all the nitty gritty details: https://huggingface.co/blog/open-r1/update-2
I am considering canceling my Pro subscription because I just discovered that i am just limited to 10 zeroGPU spaces i can host on my account. This number should be way higher.
reacted to
their
post with 🚀
6 months ago
Post
2093
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.
reacted to
alielfilali01's
post with 👍
6 months ago
Post
2133
3C3H AraGen Leaderboard welcomes today
deepseek-ai/DeepSeek-V3 and 12 other models (including the late gpt-3.5 💀) to the ranking of best LLMs in Arabic !
Observations:
- DeepSeek-v3 ranked 3rd and only Open model among the top 5 !
- A 14B open model ( Qwen/Qwen2.5-14B-Instruct) outperforms gpt-3.5-turbo-0125 (from last year). This shows how much we came in advancing and supporting Arabic presence within the LLM ecosystem !
- Contrary to what observed in likelihood-acc leaderboards (like OALL/Open-Arabic-LLM-Leaderboard) further finetuned models like maldv/Qwentile2.5-32B-Instruct actually decreased the performance compared to the original model Qwen/Qwen2.5-32B-Instruct.
It's worth to note that the decrease is statiscally insignificant which imply that at best, the out-domain finetuning do not really hurts the model original capabilities acquired during pretraining.
Previous work addressed this (finetuning VS pretraining) but more investigation in this regard is required (any PhDs here ? This could be your question ...)
Check out the latest rankings: https://huggingface.co/spaces/inceptionai/AraGen-Leaderboard
Observations:
- DeepSeek-v3 ranked 3rd and only Open model among the top 5 !
- A 14B open model ( Qwen/Qwen2.5-14B-Instruct) outperforms gpt-3.5-turbo-0125 (from last year). This shows how much we came in advancing and supporting Arabic presence within the LLM ecosystem !
- Contrary to what observed in likelihood-acc leaderboards (like OALL/Open-Arabic-LLM-Leaderboard) further finetuned models like maldv/Qwentile2.5-32B-Instruct actually decreased the performance compared to the original model Qwen/Qwen2.5-32B-Instruct.
It's worth to note that the decrease is statiscally insignificant which imply that at best, the out-domain finetuning do not really hurts the model original capabilities acquired during pretraining.
Previous work addressed this (finetuning VS pretraining) but more investigation in this regard is required (any PhDs here ? This could be your question ...)
Check out the latest rankings: https://huggingface.co/spaces/inceptionai/AraGen-Leaderboard
reacted to
their
post with ❤️
6 months ago
Post
2093
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.
posted
an
update
6 months ago
Post
2093
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.
reacted to
alielfilali01's
post with 🤗
7 months ago
Post
3544
Unpopular opinion: Open Source takes courage to do !
Not everyone is brave enough to release what they have done (the way they've done it) to the wild to be judged !
It really requires a high level of "knowing wth are you doing" ! It's kind of a super power !
Cheers to the heroes here who see this!
Not everyone is brave enough to release what they have done (the way they've done it) to the wild to be judged !
It really requires a high level of "knowing wth are you doing" ! It's kind of a super power !
Cheers to the heroes here who see this!
- 5 replies