J C's picture

J C PRO

dark-pen

·

AI & ML interests

None yet

Recent Activity

liked a Space 8 minutes ago

trellis-community/TRELLIS

reacted to mitkox's post with 🔥 8 minutes ago

I got 370 tokens/sec of Qwen3-30B-A3B 2507 on my desktop Z8 GPU workstation. My target is 400 t/s, and the last 10 % always tastes like victory!

liked a dataset 10 minutes ago

sankalpsinha77/MARVEL-40M

View all activity

Organizations

commented a paper 4 months ago

L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning

Paper • 2503.04697 • Published Mar 6 • 3 •

commented a paper 9 months ago

Explainable Multimodal Emotion Reasoning

Paper • 2306.15401 • Published Jun 27, 2023 •

commented a paper 11 months ago

MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries

Paper • 2401.15391 • Published Jan 27, 2024 • 6 •

commented 2 papers over 1 year ago

LoRA-FA: Memory-efficient Low-rank Adaptation for Large Language Models Fine-tuning

Paper • 2308.03303 • Published Aug 7, 2023 • 3 •

DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning

Paper • 2309.05173 • Published Sep 11, 2023 • 1 •