BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts
Paper
•
2408.08274
•
Published
•
13
Scaling Intelligence
university
AI & ML interests
None defined yet.
ScalingIntelligence's activity
simonguozirui
authored
2
papers
2 months ago
simonguozirui
updated
a
dataset
2 months ago
simonguozirui
published
a
dataset
2 months ago
simarora
authored
5
papers
7 months ago
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
Paper
•
2306.11698
•
Published
•
12
Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT
Paper
•
2402.07440
•
Published
•
1
Simple linear attention language models balance the recall-throughput tradeoff
Paper
•
2402.18668
•
Published
•
21
Just read twice: closing the recall gap for recurrent language models
Paper
•
2407.05483
•
Published
LoLCATs: On Low-Rank Linearizing of Large Language Models
Paper
•
2410.10254
•
Published
Bradley
authored
a
paper
9 months ago
RylanSchaeffer
authored
a
paper
11 months ago
danbider
authored
a
paper
12 months ago
ekellbuch
authored
a
paper
about 1 year ago
sabrieyuboglu
authored
a
paper
about 1 year ago
simarora
authored
5
papers
about 1 year ago
On the Opportunities and Risks of Foundation Models
Paper
•
2108.07258
•
Published
Can Foundation Models Wrangle Your Data?
Paper
•
2205.09911
•
Published
Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture
Paper
•
2310.12109
•
Published
•
1
Zoology: Measuring and Improving Recall in Efficient Language Models
Paper
•
2312.04927
•
Published
•
2
RELIC: Investigating Large Language Model Responses using Self-Consistency
Paper
•
2311.16842
•
Published
•
1
sabrieyuboglu
authored
a
paper
about 1 year ago