Feb 12, 05:17 PM

Nomic AI Releases Nomic Embed Text V2, A MoE Model With 305M Parameters, 512 Tokens, Supporting 100+ Languages

Nomic AI has announced the release of Nomic Embed Text V2, a general-purpose Mixture-of-Experts (MoE) embedding model. This model boasts state-of-the-art performance on the multilingual MIRACL benchmark for its size and supports over 100 languages. It is open source, with all training data, weights, and code available under the Apache 2.0 License. The new model features 305 million active parameters during inference and a maximum sequence length of 512 tokens. The release has been well-received in the AI community, with various experts expressing enthusiasm about its capabilities and potential applications in agentic document workflows.

#Nomic AI #Nomic Embed Text V2

Written with ChatGPT (GPT-4o mini).

Sources

deepset@deepset_ai
2 years ago
New release from our open source team @Haystack_AI with powerful upgrades for agentic pipelines!⁣ https://t.co/Utir5zVEa8
Max Woolf@minimaxir
2 years ago
Hooray, Nomic finally released a new text embedding model, I can't wait to check it out! "Active Parameters During Inference: 305M" "Maximum Sequence Length: 512 tokens" 😭 https://t.co/lXn6uibHwN
LlamaIndex 🦙@llama_index
2 years ago
A great embedding model is central to high-quality Agentic Document Workflows, so we're delighted to see this latest work from @nomic_ai! https://t.co/pezsylHNpH

Additional media

Image #1 for story nomic-ai-releases-nomic-embed-text-v2-moe-model-305m-parameters-512-tokens-100-a253ccc6