Emile's picture

3 2

Emile

EmileWesh

http://programme.zip

AI & ML interests

Emile

Recent Activity

upvoted a paper 1 day ago

Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding

upvoted a paper 8 months ago

Defeating the Training-Inference Mismatch via FP16

liked a model about 1 year ago

unsloth/Meta-Llama-3.1-70B-Instruct-bnb-4bit

View all activity

Organizations

None yet

upvoted a paper 1 day ago

Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding

Paper • 2606.21906 • Published 5 days ago • 20

upvoted a paper 8 months ago

Defeating the Training-Inference Mismatch via FP16

Paper • 2510.26788 • Published Oct 30, 2025 • 32

upvoted a paper over 1 year ago

Matryoshka Quantization

Paper • 2502.06786 • Published Feb 10, 2025 • 32