Hugging Face's logo
Olivier Dehaene's picture
TFLOPS icon 68505.6 TFLOPS
53 2 1

Olivier Dehaene

olivierdehaene
muhtasham's profile picture dacorvo's profile picture Gozde's profile picture
·

AI & ML interests

None yet

Recent Activity

updated a Space 12 days ago
olivierdehaene/balloons
View all activity

Articles

Organizations

Hugging Face's profile picture BigScience Workshop's profile picture Hugging Face Internal Testing Organization's profile picture Text Generation Inference's profile picture OpenAssistant's profile picture HuggingFaceM4's profile picture TRL's profile picture BigCode's profile picture Hugging Face H4's profile picture Hugging Face OSS Metrics's profile picture CarperAI's profile picture gg-hf's profile picture mx-test's profile picture hsramall's profile picture yorg's profile picture LLHF's profile picture SLLHF's profile picture Hugging Quants's profile picture blhf's profile picture kmhf's profile picture s0409's profile picture

olivierdehaene's activity

updated a Space 12 days ago
New activity in Alibaba-NLP/gte-Qwen2-1.5B-instruct 2 months ago

"Bidirectional attention"

2
#1 opened 5 months ago by olivierdehaene
New activity in sanchit-gandhi/whisper-jax 2 months ago

Fix Dockerfile

1
#127 opened 2 months ago by olivierdehaene
New activity in mistralai/Mistral-Nemo-Instruct-2407 3 months ago

model is not working

1
#74 opened 3 months ago by lowpex
liked a model 5 months ago
replied to mayank-mishra's post 9 months ago
view reply

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 9 months ago
Reacted to loubnabnl's post with ❤️🤯🤗 9 months ago
view post
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
New activity in BAAI/bge-reranker-large about 1 year ago

Add fast tokenizer

1
#4 opened about 1 year ago by olivierdehaene
New activity in BAAI/bge-reranker-base about 1 year ago

Add fast tokenizer

1
#5 opened about 1 year ago by olivierdehaene
New activity in HuggingFaceH4/zephyr-chat about 1 year ago

How is the model so fast and accurate?

2
#17 opened about 1 year ago by Saugatkafley
New activity in thenlper/gte-base about 1 year ago

Adding `safetensors` variant of this model
#9 opened about 1 year ago by olivierdehaene
New activity in llmrails/ember-v1 about 1 year ago

Adding `safetensors` variant of this model
#1 opened about 1 year ago by olivierdehaene
New activity in BAAI/bge-large-en-v1.5 about 1 year ago

Adding `safetensors` variant of this model
#5 opened about 1 year ago by olivierdehaene
New activity in BAAI/bge-base-en-v1.5 about 1 year ago

Adding `safetensors` variant of this model
#1 opened about 1 year ago by olivierdehaene
upvoted a paper over 1 year ago
New activity in tiiuae/falcon-7b-instruct over 1 year ago

Add hf endpoint handler.py
#24 opened over 1 year ago by olivierdehaene
New activity in tiiuae/falcon-40b-instruct over 1 year ago

Add hf endpoint handler.py
#30 opened over 1 year ago by olivierdehaene