Lukas Cavigelli

lukasc-ch's activity

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

upvoted a collection 17 days ago

Papers

Collection

2 items • Updated 13 days ago • 1

liked 9 models 17 days ago

huawei-csl/Qwen3-14B-4bit-SINQ

Text Generation • 9B • Updated 16 days ago • 42 • 5

huawei-csl/Qwen3-1.7B-4bit-SINQ

Text Generation • 1B • Updated 16 days ago • 44 • 5

huawei-csl/Qwen3-32B-4bit-ASINQ

Text Generation • 18B • Updated 16 days ago • 66 • 8

huawei-csl/Qwen3-32B-4bit-SINQ

Text Generation • 18B • Updated 16 days ago • 80 • 7

huawei-csl/Qwen3-14B-4bit-ASINQ

Text Generation • 9B • Updated 16 days ago • 73 • 6

huawei-csl/Qwen3-1.7B-4bit-ASINQ

Text Generation • 1B • Updated 16 days ago • 48 • 5

huawei-csl/Qwen3-32B-3bit-ASINQ

Text Generation • 6B • Updated 16 days ago • 136 • 5

huawei-csl/Qwen3-32B-3bit-SINQ

Text Generation • 6B • Updated 16 days ago • 162 • 5

huawei-csl/Qwen3-14B-3bit-ASINQ

Text Generation • 3B • Updated 16 days ago • 154 • 5

liked 3 models 18 days ago

huawei-csl/Qwen3-14B-3bit-SINQ

Text Generation • 3B • Updated 16 days ago • 152 • 5

huawei-csl/Qwen3-1.7B-3bit-ASINQ

Text Generation • 0.5B • Updated 16 days ago • 174 • 7

huawei-csl/Qwen3-1.7B-3bit-SINQ

Text Generation • 0.5B • Updated 16 days ago • 203 • 7

upvoted a collection 18 days ago

SINQ

Collection

This collection contains the models quantized with the SINQ quantization method. • 15 items • Updated 4 days ago • 10

authored a paper 28 days ago

AC-LoRA: (Almost) Training-Free Access Control-Aware Multi-Modal LLMs

Paper • 2505.11557 • Published May 15 • 8

updated a collection 28 days ago

Papers

Collection

2 items • Updated 13 days ago • 1

upvoted a paper 28 days ago

AC-LoRA: (Almost) Training-Free Access Control-Aware Multi-Modal LLMs

Paper • 2505.11557 • Published May 15 • 8

authored 2 papers about 1 month ago

AcceLLM: Accelerating LLM Inference using Redundancy for Load Balancing and Data Locality

Paper • 2411.05555 • Published Nov 8, 2024 • 6

SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights

Paper • 2509.22944 • Published Sep 26 • 76

upvoted a paper about 1 month ago

AcceLLM: Accelerating LLM Inference using Redundancy for Load Balancing and Data Locality

Paper • 2411.05555 • Published Nov 8, 2024 • 6