-
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 619 -
Beyond Language Models: Byte Models are Digital World Simulators
Paper • 2402.19155 • Published • 54 -
BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs
Paper • 2504.18415 • Published • 44 -
Kijai/PrecompiledWheels
Updated • 16
kas
shing3232
AI & ML interests
None yet
Recent Activity
updated
a collection
about 1 month ago
sakura
new activity
about 1 month ago
Qwen/Qwen1.5-MoE-A2.7B-Chat-GPTQ-Int4:Int4为什么比没量化的float32和float16还慢
upvoted
a
paper
about 2 months ago
TransMLA: Multi-head Latent Attention Is All You Need
Organizations
None yet