Instructions to use electroglyph/arctic-embed-l-tech_and_fiction with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use electroglyph/arctic-embed-l-tech_and_fiction with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("electroglyph/arctic-embed-l-tech_and_fiction") 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] - Transformers.js
How to use electroglyph/arctic-embed-l-tech_and_fiction with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('sentence-similarity', 'electroglyph/arctic-embed-l-tech_and_fiction'); - Notebooks
- Google Colab
- Kaggle
arctic-embed-l-tech_and_fiction
This is a finetuned version of: snowflake-arctic-embed-l
It is finetuned on a dataset of ~110K high quality synthetic examples, manually curated and edited.
The examples are primarily tech oriented, with some terms from fantasy and sci-fi fiction for good measure.
Training
For this model (Model B below) I trained at rank 128, alpha 128, with a learning rate of around 6e-6 I think, for around 10 epochs.
Benchmark Results
I've included the results for MTEB benchmark "MTEB(eng, v2)" in the results folder.
Here is a screenshot of the results summary (this is Model B):
License
arctic-embed-l-tech_and_fiction is licensed under the Apache-2. The released models can be used for commercial purposes free of charge.
Acknowledgement
Thank you to the Snowflake team for making some excellent models!
- Downloads last month
- 8
