Mixedbread
@mixedbreadai
Followers
450
Following
121
Statuses
32
Your fav. AI bakers! We're hiring: https://t.co/f4reGJwztf
Berlin, Germany
Joined March 2024
BM𝒳: A Freshly Baked Take on BM25 BMX is an eXtension of BM25. It improves the performance of the industry-standard BM25 by adding entropy-weighted similarity. 👇 Learn more in the comments👇
1
3
38
RT @juliuslipp: just revamped the hiring page of Mixedbread a bit. we're looking for amazing people to join us doing: - full stack (next.j…
0
7
0
RT @UnstructuredIO: 🚨Unstructured now supports embedding models from @mixedbreadai. 1. Ingest unstructured docs from any of 20+ sources 2…
0
3
0
RT @notrab: I posted a new tutorial on how to process embeddings with @mixedbreadai using @redpandadata and @tursodatabase ✨ Link in reply…
0
7
0
RT @juliuslipp: adding dynamic batching to our inference api back in the day was a real pain... we decided to open-source our queue, so so…
0
11
0
It even holds its own against embedding models in real world scenarios. You can try it out now: Blog: Paper: Code:
0
0
5
RT @aaxsh18: we are hiring, if you like search, genai or low level stuff (from assembly to proving complexity) please apply. https://t.co/…
0
15
0
Open Source Gets DE-licious: Mixedbread x @deepset_ai German/English Embeddings ✅ Supports binary quantization ✅ Supports MRL Model: Discord: Blog:
0
5
27
RT @jobergum: Matryoshka 🤝 Binary vectors: Slash vector search costs with Vespa We announce support for combining matryoshka and binary qu…
0
17
0
RT @jobergum: This is featured in the upcoming blog post on combining MRL with binarized embeddings. Thank you, @mixedbreadai, for the awes…
0
3
0
Follow-up on binary embeddings: 64 bytes per embedding, yee-haw 🤠 Reduces memory usage of our embedding model by more than 98% (64x) while retaining over 90% of model performance with binary 🪆 Model: Blog:
2
22
108
RT @jobergum: Support for combining Matryoshka🪆with binary quantization coming to Vespa's native hf-embedder. The example uses a model fro…
0
10
0
Wondered how to use embedding quantization with @vespaengine? Here you go. Thanks @jobergum!
Happy binary text embedding week! Created a quick notebook demonstrating: - Using @mixedbreadai embed-large-v1 model with the new sentence-transformer API for - How to index binary embeddings with HNSW indexing in @vespaengine - float-binary re-ranking!
0
1
10
RT @_philschmid: Introducing embedding quantization!💥 A new technique to quantize embeddings to achieve up to 45x faster retrieval while ke…
0
66
0
RT @tomaarsen: Embedding Quantization is here! 25x speedup in retrieval; 32x reduction in memory usage; 4x reduction in disk space; 99.3% p…
0
93
0
ColBERTus Maxiums - Introducing mxbai-colbert-large-v1 This is something for the ColBERT fans! We took our SOTA embedding model and colbertialized it. Learn more: Model: Blog:
5
20
120
👀🍞
I hear @mixedbreadai 🥖 has another pretty cool open source release ready to come out of the oven. If you like open source retrieval models it could be worthwhile to have them on your radar 👀 they’re even @jobergum-approved!
0
0
5