Youssef Boulaouane

joseph-bou's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted an article about 20 hours ago

view article

Article

Security incident disclosure — July 2026

• 

system

•

5 days ago

• 227

liked a model 5 days ago

thinkingmachines/Inkling

Image-Text-to-Text • 952B • Updated about 5 hours ago • 13.5k • • 1.26k

upvoted a collection 22 days ago

DeepSpec

Collection

12 items • Updated 22 days ago • 79

liked a model 22 days ago

litert-community/RF-DETR-Nano-LiteRT

Object Detection • Updated 19 days ago • 76 • 1

upvoted a collection 25 days ago

PP-OCRv6

Collection

From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks • 19 items • Updated Jun 15 • 104

liked 2 models about 1 month ago

zai-org/GLM-5.2

Text Generation • 753B • Updated 19 days ago • 532k • • 4.22k

ideogram-ai/ideogram-4-fp8

Text-to-Image • 9B • Updated Jun 3 • 47k • • 699

liked 2 models 3 months ago

deepseek-ai/DeepSeek-V4-Flash

Text Generation • 158B • Updated 28 days ago • 2.89M • • 1.78k

deepseek-ai/DeepSeek-V4-Pro

Text Generation • 862B • Updated 28 days ago • 1.46M • • 5.27k

upvoted a collection 3 months ago

Branch-Adapt-Route

Collection

Artifacts for Branch-Adapt-Route • 9 items • Updated Apr 20 • 9

liked 2 models 3 months ago

moonshotai/Kimi-K2.6

Image-Text-to-Text • 1.1T • Updated May 19 • 1.19M • • 1.54k

Qwen/Qwen3.6-35B-A3B

Image-Text-to-Text • 36B • Updated Apr 24 • 5.95M • • 2.44k

reacted to danielhanchen's post with 🔥 3 months ago

view post

Post

5581

You can now fine-tune Gemma 4 for free with our notebooks! 🔥

You just need 8GB VRAM to train Gemma 4 locally!

Unsloth trains Gemma4 1.5x faster with 50% less VRAM.
GitHub: https://github.com/unslothai/unsloth
Guide + Notebooks: https://unsloth.ai/docs/models/gemma-4/train

See translation

• 
• 

• 
• 
• 
• 5 replies

·

🔥

20

20

🚀

9

9

❤️

4

4

+

Reply

liked 3 models 4 months ago

google/gemma-4-31B-it

Image-Text-to-Text • 33B • Updated about 6 hours ago • 12M • • 3.3k

google/gemma-4-26B-A4B-it

Image-Text-to-Text • 27B • Updated about 6 hours ago • 13.2M • • 1.3k

netflix/void-model

Video-to-Video • Updated Apr 6 • 960

upvoted 2 collections 4 months ago

EUPE

Collection

6 items • Updated Mar 30 • 29

Gemma 4

Collection

15 items • Updated Jun 10 • 1.04k

liked a model 4 months ago

google/gemma-4-E2B-it

Any-to-Any • 5B • Updated about 6 hours ago • 2.95M • 827

reacted to omarkamali's post with 🚀 4 months ago

view post

Post

1897

I just might have cracked tokenizer-free LLMs. No vocab, no softmax.

I'm training a 22M params LLM rn to test this "thing" and it's able to formulate coherent sentences 🤯

Bear in mind, this is a completely new, tokenizer-free LLM architecture with built-in language universality.

Check the explainer video to understand what's happening. Feedback welcome on this approach!

See translation

• 
• 
• 

• 
• 
• 
• 14 replies

·

🚀

4

4

🤯

2

2

🔥

1

1

+

Reply