Shreyas Jagannath

jaggernaut007's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

published a model 1 day ago

jaggernaut007/kkn

4B • Updated 1 day ago • 12

updated a model 1 day ago

jaggernaut007/kkn

4B • Updated 1 day ago • 12

updated 12 models about 2 years ago

jaggernaut007/roberta-base-finetuned-abbr-finetuned-ner

Token Classification • 0.1B • Updated May 7, 2024 • 8

jaggernaut007/keyphrase-extraction-distilbert-inspec-finetuned-ner

Token Classification • 66.4M • Updated Apr 25, 2024 • 5

jaggernaut007/albert-large-v2-finetuned-abbDet-finetuned-ner

Token Classification • 16.6M • Updated Apr 22, 2024 • 5

jaggernaut007/bert-base-NER-finetuned-ner

Token Classification • 0.1B • Updated Apr 22, 2024 • 11

jaggernaut007/roberta-base-biomedical-clinical-es-finetuned-ner-CRAFT_AugmentedTransfer_ES-finetuned-ner

Token Classification • 0.1B • Updated Apr 22, 2024 • 7

jaggernaut007/Medical-NER-finetuned-ner

Token Classification • 0.2B • Updated Apr 22, 2024 • 13

jaggernaut007/albert-large-v2-finetuned-abbDet-finetuned-ner-Custom

Token Classification • 16.6M • Updated Apr 18, 2024 • 7

jaggernaut007/roberta-base-finetuned-abbr-finetuned-ner-Custom

Updated Apr 18, 2024

jaggernaut007/roberta-large-finetuned-abbr-finetuned-ner

Token Classification • 0.4B • Updated Apr 15, 2024 • 5

jaggernaut007/roberta-large-finetuned-abbr-filtered-plod-finetuned-ner

Token Classification • 0.4B • Updated Apr 14, 2024 • 10

jaggernaut007/biomedical-ner-all-finetuned-ner

Updated Apr 14, 2024

jaggernaut007/KoELECTRA-small-v3-modu-ner-finetuned-ner

Updated Apr 13, 2024

upvoted a paper about 2 years ago

3D Gaussian Splatting for Real-Time Radiance Field Rendering

Paper • 2308.04079 • Published Aug 8, 2023 • 203

updated a model about 2 years ago

jaggernaut007/militaryAircraftResnest

Updated Mar 28, 2024

reacted to tomaarsen's post with 🔥 about 2 years ago

view post

Post

3262

🏅 Quantized Embeddings are here! Unlike model quantization, embedding quantization is a post-processing step for embeddings that converts e.g. float32 embeddings to binary or int8 embeddings. This saves 32x or 4x memory & disk space, and these embeddings are much easier to compare!

Our results show 25-45x speedups in retrieval compared to full-size embeddings, while keeping 96% of the performance!

Learn more about it in our blogpost in collaboration with mixedbread.ai: https://huggingface.co/blog/embedding-quantization
Or try out our demo where we use quantized embeddings to let you search all of Wikipedia (yes, 41,000,000 texts) in 1 second on a CPU Space: sentence-transformers/quantized-retrieval

• 
• 
• 2 replies

·

🔥

14

14

❤️

10

10

+

Reply