Nomic Embed
Collection
Open Source Long Context Text Embedders • 8 items • Updated • 24
nomic-embed-text-v1-ablated: A Reproducible Long Context (8192) Text Embedder
nomic-embed-text-v1-ablated is 8192 context length text encoder. This is a checkpoint trained after modifying the training dataset to be different from the dataset used to train our final model. The purpose of releasing this checkpoint is to understand the impact that subsets of our training data had on model outcomes. This release is part of our commitment to open-source training artifacts from our Nomic Embed Text tech report here
If you want to use a model to extract embeddings, we suggest using nomic-embed-text-v1.
Join the Nomic Community
- Nomic: https://nomic.ai
- Discord: https://discord.gg/myY5YDR8z8
- Twitter: https://twitter.com/nomic_ai
- Downloads last month
- 168
Model tree for nomic-ai/nomic-embed-text-v1-ablated
Spaces using nomic-ai/nomic-embed-text-v1-ablated 24
Collection including nomic-ai/nomic-embed-text-v1-ablated
Paper for nomic-ai/nomic-embed-text-v1-ablated
Evaluation results
- accuracy on MTEB AmazonCounterfactualClassification (en)test set self-reported78.672
- ap on MTEB AmazonCounterfactualClassification (en)test set self-reported42.738
- f1 on MTEB AmazonCounterfactualClassification (en)test set self-reported72.800
- accuracy on MTEB AmazonPolarityClassificationtest set self-reported90.414
- ap on MTEB AmazonPolarityClassificationtest set self-reported87.088
- f1 on MTEB AmazonPolarityClassificationtest set self-reported90.392
- accuracy on MTEB AmazonReviewsClassification (en)test set self-reported47.808
- f1 on MTEB AmazonReviewsClassification (en)test set self-reported47.257
from sentence_transformers import SentenceTransformer model = SentenceTransformer("nomic-ai/nomic-embed-text-v1-ablated", trust_remote_code=True) sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4]