Nomic‑Embed‑Text (also known as nomic‑embed‑text‑v1/v1.5) is an open-source long-context text embedding model supporting up to 8192 tokens. It outperforms OpenAI’s text‑embedding‑ada‑002 and text‑embedding‑3‑small on both short and long-context embedding benchmarks.

• Architecture: Built on a BERT backbone extended to 2048 context (nomic‑bert‑2048) with contrastive multi-stage training, using Rotary position embeddings and SwiGLU activations for improved representation.
• Strong Benchmark Results: Excels on MTEB, LoCo, and other long-context retrieval tasks, surpassing models in its parameter class.
• Fully Open-Source: Model weights, training code, and dataset are released under Apache‑2.0, ensuring reproducibility and auditability.
• v1.5 Enhancements: Adds Matryoshka representation learning for dynamic dimensionality reduction, and supports deployment via ONNX, Transformers.js, and more

The source model can be found here

When the user has fine-tuned the source model, the model conversion process must be performed again.

Users can refer to either of the following two methods to complete the model conversion:

• Using AIMO for model conversion: Click Model Conversion Reference in the Performance Reference section on the right to view the conversion steps.

• Using Qualcomm QNN for model conversion: Please refer to the Qualcomm QNN Documentation.

The model performance benchmarks and example code provided by Model Farm are all implemented based on the APLUX AidLite SDK.

For models in .bin format, you can use either of the following two inference engines to run inference on Qualcomm chips:

Inference using APLUX AidLite: please refer to the APLUX AidLite Developer Documentation

Inference using Qualcomm QNN: Please refer to the Qualcomm QNN Documentation

Inference Example Code

The inference example code is implemented using the AidLite SDK.

Click Model & Code to download the model files and the inference code package. The file structure is as follows:

/model_farm_{model_name}_aidlite
    
    |__ models # folder where model files are stored

    |__ python # aidlite python model inference example

    |__ cpp # aidlite cpp model inference example

    |__ README.md