20 4 18

John Locke

johnlockejrr

[email protected]

AI & ML interests

NLP, OCR, AI

Recent Activity

reacted to onekq's post with 👍 5 days ago

QwQ-32B is amazing! It ranks below o1-preview, but beats DeepSeek v3 and all Gemini models. https://huggingface.co/spaces/onekq-ai/WebApp1K-models-leaderboard Now we have such a powerful model that can fit into a single GPU, can someone finetune a web app model to push SOTA of my leaderboard? 🤗

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

View all activity

Organizations

None yet

johnlockejrr's activity

reacted to onekq's post with 👍 5 days ago

Post

3222

QwQ-32B is amazing!

It ranks below o1-preview, but beats DeepSeek v3 and all Gemini models.
onekq-ai/WebApp1K-models-leaderboard

Now we have such a powerful model that can fit into a single GPU, can someone finetune a web app model to push SOTA of my leaderboard? 🤗

1 reply

reacted to MohamedRashad's post with ❤️ 10 days ago

Post

3411

I think we have released the best Arabic model under 25B at least based on 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 🌙

1 reply

liked a Space 13 days ago

Yehia 7B Preview

💬

Good Arabic Model

upvoted a collection about 1 month ago

DictaBERT

Collection

Collection of state-of-the-art language model for Hebrew, finetuned for various tasks, as detailed in the article: https://arxiv.org/abs/2308.16687 • 17 items • Updated Apr 4, 2024 • 5

liked a model about 1 month ago

stepfun-ai/GOT-OCR2_0

Image-Text-to-Text • Updated Feb 4 • 76.9k • 1.42k

reacted to victor's post with 🚀 about 1 month ago

Post

3053

Finally, an open-source AI that turns your lyrics into full songs is here—meet YuE! Unlike other tools that only create short clips, YuE can make entire songs (up to 5 minutes) with vocals, melody, and instruments all working together. Letsss go!

m-a-p/YuE-s1-7B-anneal-en-cot

liked a Space about 1 month ago

HTRFLOW

🏢

htrflow demo app

New activity in Teklia/pylaia-belfort about 2 months ago

PyLaia enhancement

#7 opened about 2 months ago by

johnlockejrr

published a Space about 2 months ago

Yolo Pylaia

📈

Samaritan OCR with YOLOv8 and PyLaia

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

reacted to singhsidhukuldeep's post with 🚀 3 months ago

Post

3702

Exciting breakthrough in AI: @Meta 's new Byte Latent Transformer (BLT) revolutionizes language models by eliminating tokenization!

The BLT architecture introduces a groundbreaking approach that processes raw bytes instead of tokens, achieving state-of-the-art performance while being more efficient and robust. Here's what makes it special:

>> Key Innovations
Dynamic Patching: BLT groups bytes into variable-sized patches based on entropy, allocating more compute power where the data is more complex. This results in up to 50% fewer FLOPs during inference compared to traditional token-based models.

Three-Component Architecture:
• Lightweight Local Encoder that converts bytes to patch representations
• Powerful Global Latent Transformer that processes patches
• Local Decoder that converts patches back to bytes

>> Technical Advantages
• Matches performance of Llama 3 at 8B parameters while being more efficient
• Superior handling of non-English languages and rare character sequences
• Remarkable 99.9% accuracy on spelling tasks
• Better scaling properties than token-based models

>> Under the Hood
The system uses an entropy model to determine patch boundaries, cross-attention mechanisms for information flow, and hash n-gram embeddings for improved representation. The architecture allows simultaneous scaling of both patch and model size while maintaining fixed inference costs.

This is a game-changer for multilingual AI and could reshape how we build future language models. Excited to see how this technology evolves!

3 replies

liked a Space 3 months ago

Ituria

🏃

Search for information using AI-driven queries

New activity in Gabriel/Qwen2-VL-2B-Instruct 3 months ago

Model inference

#1 opened 3 months ago by

johnlockejrr

reacted to MohamedRashad's post with ❤️❤️ 3 months ago

Post

1691

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