BitNet a4.8: 4-bit Activations for 1-bit LLMs
Paper
•
2411.04965
•
Published
•
63
•
6
Timothe Laborie
timothelaborie
AI & ML interests
ML
Recent Activity
upvoted
a
paper
25 days ago
Cautious Optimizers: Improving Training with One Line of Code
commented
a paper
about 1 month ago
BitNet a4.8: 4-bit Activations for 1-bit LLMs
upvoted
a
paper
about 1 month ago
BitNet a4.8: 4-bit Activations for 1-bit LLMs
Organizations
timothelaborie's activity
commented
a
paper
about 1 month ago
[FEEDBACK] Daily Papers
102
#32 opened 6 months ago
by
kramp
commented
a
paper
3 months ago
Fine Tuning for Classification
6
#129 opened 10 months ago
by
MUHAMMAD-SOHAIL-ZZU
triton 3
2
#3 opened 5 months ago
by
timothelaborie
commented
a
paper
7 months ago
commented
a
paper
8 months ago
Why are these models fp32?
5
#2 opened 9 months ago
by
supercharge19
commented
a
paper
9 months ago
commented
5
papers
10 months ago
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper
•
2402.17764
•
Published
•
603
•
142
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper
•
2402.17764
•
Published
•
603
•
142
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper
•
2402.17764
•
Published
•
603
•
142
GPTVQ: The Blessing of Dimensionality for LLM Quantization
Paper
•
2402.15319
•
Published
•
19
•
3
BitDelta: Your Fine-Tune May Only Be Worth One Bit
Paper
•
2402.10193
•
Published
•
19
•
5
commented
5
papers
11 months ago
TP-Aware Dequantization
Paper
•
2402.04925
•
Published
•
3
•
2
BlackMamba: Mixture of Experts for State-Space Models
Paper
•
2402.01771
•
Published
•
23
•
5
EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
Paper
•
2401.15077
•
Published
•
19
•
6
EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
Paper
•
2401.15077
•
Published
•
19
•
6
FP6-LLM: Efficiently Serving Large Language Models Through FP6-Centric Algorithm-System Co-Design
Paper
•
2401.14112
•
Published
•
18
•
7
commented
a
paper
12 months ago