Article
Speeding Up LLM Decoding with Advanced Universal Assisted Generation Techniques
By
and 8 others
•
•
8Moshe Wasserblat
moshew
AI & ML interests
NLP Efficiency, Sentiment Analysis, Few-shot learning, Distillation
Recent Activity
published
an
article
about 21 hours ago
Speeding Up LLM Decoding with Advanced Universal Assisted Generation Techniques
liked
a model
14 days ago
ai21labs/AI21-Jamba-Mini-1.6
authored
a paper
about 1 month ago
SQuARE: Sequential Question Answering Reasoning Engine for Enhanced
Chain-of-Thought in Large Language Models
Organizations
moshew's activity
published
an
article
about 21 hours ago
liked
a
model
14 days ago
authored
a
paper
about 1 month ago
upvoted
a
paper
about 1 month ago
upvoted
a
paper
4 months ago
published
an
article
5 months ago
Article
Universal Assisted Generation: Faster Decoding with Any Assistant Model
By
and 7 others
•
•
52
Running few-shot SetFit 5 samples with "dunzhang/stella_en_400M_v5" results 95.7% Accuracy
#1 opened 5 months ago
by
moshew
"jxm/cde-small-v1" doesnt load with SetFitModel.from_pretrained
1
#5 opened 5 months ago
by
moshew
published
an
article
6 months ago
Article
Faster Assisted Generation with Dynamic Speculation
By
and 6 others
•
•
46
Text Classification with LLMs
7
#30 opened 7 months ago
by
dss107
upvoted
2
papers
7 months ago
authored
a
paper
8 months ago
upvoted
a
paper
10 months ago
authored
a
paper
10 months ago
published
an
article
12 months ago
Article
Blazing Fast SetFit Inference with 🤗 Optimum Intel on Xeon
By
and 5 others
•
•
11
liked
a
model
12 months ago
published
an
article
about 1 year ago
Article
A Chatbot on your Laptop: Phi-2 on Intel Meteor Lake
By
and 5 others
•
•
6
published
an
article
about 1 year ago
Article
CPU Optimized Embeddings with 🤗 Optimum Intel and fastRAG
By
and 5 others
•
•
9
updated
a
model
about 1 year ago