Thibault Castells

thibcastells's activity

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

upvoted 2 collections about 15 hours ago

Efficient MoE-based LLM

Collection

Mixture-of-Experts Large Language Models with Advanced Quantization • 4 items • Updated 1 day ago • 18

Efficient Large Vision-Language Model

Collection

ERGO: LVLM trained with RL on efficiency objectives; https://github.com/nota-github/ERGO • 3 items • Updated 1 day ago • 20

authored 2 papers almost 2 years ago

Shortened LLaMA: A Simple Depth Pruning for Large Language Models

Paper • 2402.02834 • Published Feb 5, 2024 • 17

EdgeFusion: On-Device Text-to-Image Generation

Paper • 2404.11925 • Published Apr 18, 2024 • 23

upvoted a paper almost 2 years ago

EdgeFusion: On-Device Text-to-Image Generation

Paper • 2404.11925 • Published Apr 18, 2024 • 23

authored a paper about 2 years ago

Automatic Neural Network Pruning that Efficiently Preserves the Model Accuracy

Paper • 2111.09635 • Published Nov 18, 2021 • 1

New activity in laion/clap-htsat-unfused over 2 years ago

Use most recent checkpoints

4

#2 opened over 2 years ago by

thibcastells

liked 2 models over 2 years ago

nota-ai/coreml-bk-sdm

Text-to-Image • Updated Nov 17, 2023 • 7

Phind/Phind-CodeLlama-34B-Python-v1

Text Generation • Updated Aug 26, 2023 • 874 • 252

updated a model over 2 years ago

thibcastells/coreml-bk-sdm

Updated Aug 23, 2023

liked a Space over 2 years ago

Running

Featured

114

Compressed Stable Diffusion

🌟

114

Compare image generation results from original and compressed AI models

authored a paper over 2 years ago

On Architectural Compression of Text-to-Image Diffusion Models

Paper • 2305.15798 • Published May 25, 2023 • 5