54 3 1

Olivier Dehaene

olivierdehaene

olivierdehaene

AI & ML interests

None yet

Recent Activity

upvoted an article 22 days ago

The Transformers Library: standardizing model definitions

new activity 6 months ago

mistral-community/Pixtral-Large-Instruct-2411:🚩 Report: Legal issue(s)

new activity 9 months ago

Alibaba-NLP/gte-Qwen2-1.5B-instruct:"Bidirectional attention"

View all activity

Organizations

olivierdehaene's activity

upvoted an article 22 days ago

Article

The Transformers Library: standardizing model definitions

and 3 others •

23 days ago

• 110

New activity in mistral-community/Pixtral-Large-Instruct-2411 6 months ago

🚩 Report: Legal issue(s)

#1 opened 6 months ago by

patrickvonplaten

New activity in Alibaba-NLP/gte-Qwen2-1.5B-instruct 9 months ago

"Bidirectional attention"

#1 opened 11 months ago by

olivierdehaene

New activity in mistralai/Mistral-Nemo-Instruct-2407 10 months ago

model is not working

😔 ➕ 4

#74 opened 10 months ago by

lowpex

liked a model 12 months ago

raidium/MQG

Text Generation • Updated Jul 10, 2024 • 25 • 3

replied to mayank-mishra's post about 1 year ago

Nice blog!
@osanseviero we have been doing this in TGI and TEI for a while ;)
Padding free implementations also make dynamic batching easier to implement and more predictable in memory.

authored a paper over 1 year ago

StarCoder 2 and The Stack v2: The Next Generation

Paper • 2402.19173 • Published Feb 29, 2024 • 147

reacted to loubnabnl's post with ❤️🤯🤗 over 1 year ago

Post

⭐ Today we’re releasing The Stack v2 & StarCoder2: a series of 3B, 7B & 15B code generation models trained on 3.3 to 4.5 trillion tokens of code:

- StarCoder2-15B matches or outperforms CodeLlama 34B, and approaches DeepSeek-33B on multiple benchmarks.
- StarCoder2-3B outperforms StarCoderBase-15B and similar sized models.
- The Stack v2 a 4x larger dataset than the Stack v1, resulting in 900B unique code tokens 🚀
As always, we released everything from models and datasets to curation code. Enjoy!

🔗 StarCoder2 collection: bigcode/starcoder2-65de6da6e87db3383572be1a
🔗 Paper: https://drive.google.com/file/d/17iGn3c-sYNiLyRSY-A85QOzgzGnGiVI3/view
🔗 BlogPost: https://huggingface.co/blog/starcoder2
🔗 Code Leaderboard: bigcode/bigcode-models-leaderboard