535
Scaling test-time compute
📈
Enhance math problem solving by scaling test-time compute
Pretam Ray
Pretam
AI & ML interests
NLP
Recent Activity
liked
a Space
17 days ago
HuggingFaceH4/blogpost-scaling-test-time-compute
liked
a Space
24 days ago
hf-accelerate/model-memory-usage
published
a model
about 2 months ago
Pretam/t5-small-finetuned-xsum
Organizations
Pretam's activity
liked
a
Space
17 days ago
liked
a
Space
24 days ago
published
a
model
about 2 months ago
upvoted
an
article
9 months ago
Article
Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA
•
129
reacted to
vladbogo's
post with 👍
about 1 year ago
Post
A recent paper titled "ShortGPT: Layers in Large Language Models are More Redundant Than You Expect" proposes a simple and effective approach to pruning Large Language Models (LLMs) by removing redundant layers.
Key points:
* Discovers significant redundancy across layers in LLMs, with some layers playing a negligible role for the final performance.
* Defines a new metric called Block Influence (BI) to quantify the importance of each layer in an LLM.
* Removes layers with low BI scores, achieving up to 25% reduction in parameters and computation while maintaining 92% of the LLM's performance.
Congrats to the authors for their work!
Paper: ShortGPT: Layers in Large Language Models are More Redundant Than You Expect (2403.03853)
Key points:
* Discovers significant redundancy across layers in LLMs, with some layers playing a negligible role for the final performance.
* Defines a new metric called Block Influence (BI) to quantify the importance of each layer in an LLM.
* Removes layers with low BI scores, achieving up to 25% reduction in parameters and computation while maintaining 92% of the LLM's performance.
Congrats to the authors for their work!
Paper: ShortGPT: Layers in Large Language Models are More Redundant Than You Expect (2403.03853)
upvoted
a
paper
about 1 year ago
liked
a
Space
about 1 year ago
liked
a
model
about 1 year ago
reacted to
SkalskiP's
post with ❤️
about 1 year ago
Post
YOLO-World: Real-Time, Zero-Shot Object Detection 🔥 🔥 🔥
YOLO-World was designed to solve a limitation of existing zero-shot object detection models: speed. Whereas other state-of-the-art models use Transformers, a powerful but typically slower architecture, YOLO-World uses the faster CNN-based YOLO architecture.
YOLO-World provides three models: small with 13M (re-parametrized 77M), medium with 29M (re-parametrized 92M), and large with 48M (re-parametrized 110M) parameters.
The YOLO-World team benchmarked the model on the LVIS dataset and measured their performance on the V100 without any performance acceleration mechanisms like quantization or TensorRT.
According to the paper, YOLO-World reached 35.4 AP with 52.0 FPS for the L version and 26.2 AP with 74.1 FPS for the S version. While the V100 is a powerful GPU, achieving such high FPS on any device is impressive.
- 🔗 YOLO-World arXiv paper: https://lnkd.in/ddRBKCCX
- 🔗 my YOLO-World technical report: https://blog.roboflow.com/what-is-yolo-world
- 🤗 YOLO-World space: SkalskiP/YOLO-World
YOLO-World was designed to solve a limitation of existing zero-shot object detection models: speed. Whereas other state-of-the-art models use Transformers, a powerful but typically slower architecture, YOLO-World uses the faster CNN-based YOLO architecture.
YOLO-World provides three models: small with 13M (re-parametrized 77M), medium with 29M (re-parametrized 92M), and large with 48M (re-parametrized 110M) parameters.
The YOLO-World team benchmarked the model on the LVIS dataset and measured their performance on the V100 without any performance acceleration mechanisms like quantization or TensorRT.
According to the paper, YOLO-World reached 35.4 AP with 52.0 FPS for the L version and 26.2 AP with 74.1 FPS for the S version. While the V100 is a powerful GPU, achieving such high FPS on any device is impressive.
- 🔗 YOLO-World arXiv paper: https://lnkd.in/ddRBKCCX
- 🔗 my YOLO-World technical report: https://blog.roboflow.com/what-is-yolo-world
- 🤗 YOLO-World space: SkalskiP/YOLO-World
upvoted
a
paper
about 1 year ago
liked
a
model
over 1 year ago
[bot] Conversion to Parquet
#1 opened over 1 year ago
by
parquet-converter
updated
a
dataset
over 1 year ago
upvoted
a
paper
over 1 year ago
updated
4
datasets
over 1 year ago
Dataset Generation Error when loading this dataset using load_dataset('MultiCoNER/multiconer_v2' ,'English (EN)')
1
#1 opened almost 2 years ago
by
Pretam
liked
a
model
almost 2 years ago
