Hugging Face's logo
Mohamed Rashad's picture
71 8 83

Mohamed Rashad PRO

MohamedRashad
hotbizza's profile picture Lns9777's profile picture avatar9692's profile picture
·

AI & ML interests

Computer Vision, Robotics, Natural Language Processing

Recent Activity

new activity about 7 hours ago
MohamedRashad/Flux-Redux:Flux-Redux Paused Status
new activity about 18 hours ago
MohamedRashad/Infinity:Fixes 500 error for some users
updated a Space 1 day ago
MohamedRashad/arabic-tokenizers-leaderboard
View all activity

Organizations

Navid AI's profile picture

MohamedRashad's activity

reacted to their post with 🔥 13 days ago
posted an update 13 days ago
reacted to lewtun's post with ❤️ 13 days ago
view post
Post
4477
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
replied to Keltezaa's post 19 days ago
view reply

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 🚀 about 2 months ago
view post
Post
2071
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.
reacted to alielfilali01's post with 👍 about 2 months ago
view post
Post
2021
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: inceptionai/AraGen-Leaderboard
reacted to their post with ❤️ about 2 months ago
view post
Post
2071
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.
posted an update about 2 months ago
view post
Post
2071
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.
reacted to alielfilali01's post with 🤗 2 months ago
view post
Post
3475
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!
·
reacted to their post with 🔥 2 months ago
posted an update 2 months ago
reacted to their post with 🚀 3 months ago
posted an update 3 months ago
posted an update 3 months ago
reacted to their post with 👀 5 months ago
posted an update 5 months ago
reacted to reach-vb's post with 🧠 5 months ago
view post
Post
2892
Less than two days ago Kyutai Labs open sourced Moshi - an ~7.6B on-device Speech to Speech foundation model and Mimi - SoTA streaming speech codec! 🔥

The release includes:

1. Moshiko & Moshika - Moshi finetuned on synthetic data (CC-BY license) ( kyutai/moshi-v01-release-66eaeaf3302bef6bd9ad7acd)
2. Mimi - Streaiming Audio Codec, processes 24 kHz audio, down to a 12.5 Hz representation with a bandwidth of 1.1 kbps (CC-BY license) ( kyutai/mimi)
3. Model checkpoints & Inference codebase written in Rust (Candle), PyTorch & MLX (Apache license) (https://github.com/kyutai-labs/moshi)

How does Moshi work?

1. Moshi processes two audio streams: one for itself and one for the user, with the user's stream coming from audio input and Moshi's stream generated by the model.

2. Along with these audio streams, Moshi predicts text tokens for its speech, enhancing its generation quality.

3. The model uses a small Depth Transformer for codebook dependencies and a large 7B parameter Temporal Transformer for temporal dependencies.

4. The theoretical latency is 160ms, with a practical latency of around 200ms on an L4 GPU.

Model size & inference:

Moshiko/ka are 7.69B param models

bf16 ~16GB VRAM
8-bit ~8GB VRAM
4-bit ~4GB VRAM

You can run inference via Candle 🦀, PyTorch and MLX - based on your hardware.

The Kyutai team, @adefossez @lmz and team are cracked AF, they're bringing some serious firepower to the open source/ science AI scene, looking forward to what's next! 🐐
  • 1 reply
·
reacted to their post with ❤️ 5 months ago
view post
Post
3447
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 ^_^
posted an update 5 months ago
view post
Post
3447
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 ^_^
reacted to rwightman's post with ❤️ 6 months ago
view post
Post
1296
The timm leaderboard timm/leaderboard has been updated with the ability to select different hardware benchmark sets: RTX4090, RTX3090, two different CPUs along with some NCHW / NHWC layout and torch.compile (dynamo) variations.

Also worth pointing out, there are three rather newish 'test' models that you'll see at the top of any samples/sec comparison:
* test_vit ( timm/test_vit.r160_in1k)
* test_efficientnet ( timm/test_efficientnet.r160_in1k)
* test_byobnet ( timm/test_byobnet.r160_in1k, a mix of resnet, darknet, effnet/regnet like blocks)

They are < 0.5M params, insanely fast and originally intended for unit testing w/ real weights. They have awful ImageNet top-1, it's rare to have anyone bother to train a model this small on ImageNet (the classifier is roughly 30-70% of the param count!). However, they are FAST on very limited hadware and you can fine-tune them well on small data. Could be the model you're looking for?