jesse
@jn2clark.bsky.social
Founder @marqo_ai, multimodal search, http://github.com/marqo-ai/marqo. Made robots see & learn @ Amazon RAI. Ex physicist @ Stanford & UCL, http://jn2clark.github.io
Blog: marqo.ai/blog/introdu...
GitHub: github.com/marqo-ai/mar...
Hugging Face: huggingface.co/collections/...
GitHub: github.com/marqo-ai/mar...
Hugging Face: huggingface.co/collections/...
Introducing Marqo Specialized Embedding Models for Ecommerce: Powering Multimodal AI Search
We have launched two foundation models for ecommerce that deliver much higher performance for product search and recommendations. These models excel in generating multimodal product embeddings from im...
marqo.ai
November 24, 2024 at 10:01 PM
Blog: marqo.ai/blog/introdu...
GitHub: github.com/marqo-ai/mar...
Hugging Face: huggingface.co/collections/...
GitHub: github.com/marqo-ai/mar...
Hugging Face: huggingface.co/collections/...
+ Released 2 evaluation datasets: GoogleShopping-1m and AmazonProducts-3m.
+ Released evaluation code.
+ Apache 2.0 model weights available on @huggingface
and to test out on Hugging Face Spaces.
+ Released evaluation code.
+ Apache 2.0 model weights available on @huggingface
and to test out on Hugging Face Spaces.
November 24, 2024 at 10:01 PM
+ Released 2 evaluation datasets: GoogleShopping-1m and AmazonProducts-3m.
+ Released evaluation code.
+ Apache 2.0 model weights available on @huggingface
and to test out on Hugging Face Spaces.
+ Released evaluation code.
+ Apache 2.0 model weights available on @huggingface
and to test out on Hugging Face Spaces.
+ Up to 231% improvement over other bench-marked models (see blog below).
+ Evaluated on over 4M products across 10,000's of categories.
+ Detailed performance comparisons across three major tasks: Text2Image, Category2Image, and AmazonProducts-Text2Image.
+ Evaluated on over 4M products across 10,000's of categories.
+ Detailed performance comparisons across three major tasks: Text2Image, Category2Image, and AmazonProducts-Text2Image.
November 24, 2024 at 10:01 PM
+ Up to 231% improvement over other bench-marked models (see blog below).
+ Evaluated on over 4M products across 10,000's of categories.
+ Detailed performance comparisons across three major tasks: Text2Image, Category2Image, and AmazonProducts-Text2Image.
+ Evaluated on over 4M products across 10,000's of categories.
+ Detailed performance comparisons across three major tasks: Text2Image, Category2Image, and AmazonProducts-Text2Image.
+ Up to 88% improvement on the best private model, Amazon-Titan-Multimodal (and better than Google Vertex, Cohere).
+ Up to 31% improvement on the best open source model, ViT-SO400M-14-SigLIP.
+ 5ms single text/image inference (A10g).
+ Up to 31% improvement on the best open source model, ViT-SO400M-14-SigLIP.
+ 5ms single text/image inference (A10g).
November 24, 2024 at 10:01 PM
+ Up to 88% improvement on the best private model, Amazon-Titan-Multimodal (and better than Google Vertex, Cohere).
+ Up to 31% improvement on the best open source model, ViT-SO400M-14-SigLIP.
+ 5ms single text/image inference (A10g).
+ Up to 31% improvement on the best open source model, ViT-SO400M-14-SigLIP.
+ 5ms single text/image inference (A10g).
Marqo ecommerce models significantly outperform models from Amazon, Google, Cohere and Jina (see below).
Fun fact: we had to create a significantly smaller and easier evaluation dataset just to accommodate some of the private models!
Fun fact: we had to create a significantly smaller and easier evaluation dataset just to accommodate some of the private models!
November 24, 2024 at 10:01 PM
Marqo ecommerce models significantly outperform models from Amazon, Google, Cohere and Jina (see below).
Fun fact: we had to create a significantly smaller and easier evaluation dataset just to accommodate some of the private models!
Fun fact: we had to create a significantly smaller and easier evaluation dataset just to accommodate some of the private models!