jclian91/math-solver
Viewer
•
Updated
•
4.78k
•
73
jclian91
jclian91
·
AI & ML interests
None yet
Recent Activity
updated
a dataset
3 days ago
jclian91/math-solver
published
a dataset
6 days ago
jclian91/math-solver
liked
a dataset
8 days ago
trl-lib/math_shepherd
Organizations
None yet
jclian91's activity
updated
a
dataset
3 days ago
published
a
dataset
6 days ago
liked
a
dataset
8 days ago
updated
a
dataset
9 days ago
liked
a
model
3 months ago
updated
a
Space
3 months ago
updated
a
model
6 months ago
updated
a
Space
7 months ago
[bot] Conversion to Parquet
#1 opened 9 months ago
by
parquet-converter
updated
a
dataset
9 months ago
[bot] Conversion to Parquet
#1 opened 9 months ago
by
parquet-converter
updated
a
dataset
9 months ago
liked
a
model
12 months ago
reacted to
akhaliq's
post with ❤️
about 1 year ago
Post
In Search of Needles in a 10M Haystack
Recurrent Memory Finds What LLMs Miss
paper addresses the challenge of processing long documents using generative transformer models. To evaluate different approaches, we introduce BABILong, a new benchmark designed to assess model capabilities in extracting and processing distributed facts within extensive texts. Our evaluation, which includes benchmarks for GPT-4 and RAG, reveals that common methods are effective only for sequences up to 10^4 elements. In contrast, fine-tuning GPT-2 with recurrent memory augmentations enables it to handle tasks involving up to 10^7 elements. This achievement marks a substantial leap, as it is by far the longest input processed by any open neural network model to date, demonstrating a significant improvement in the processing capabilities for long sequences
Recurrent Memory Finds What LLMs Miss
paper addresses the challenge of processing long documents using generative transformer models. To evaluate different approaches, we introduce BABILong, a new benchmark designed to assess model capabilities in extracting and processing distributed facts within extensive texts. Our evaluation, which includes benchmarks for GPT-4 and RAG, reveals that common methods are effective only for sequences up to 10^4 elements. In contrast, fine-tuning GPT-2 with recurrent memory augmentations enables it to handle tasks involving up to 10^7 elements. This achievement marks a substantial leap, as it is by far the longest input processed by any open neural network model to date, demonstrating a significant improvement in the processing capabilities for long sequences
liked
a
model
about 1 year ago
updated
a
dataset
over 1 year ago
liked
a
model
over 1 year ago
updated
a
dataset
over 1 year ago