Skip to content

Using custom fine-tuned weights with embed.text #68

Description

@dipamgoswami

Hi,

I see that the nomic embedding model can be selected based on the model_name as follows:

from nomic import embed

output = embed.text(
    texts=['Nomic Embedding API', '#keepAIOpen'],
    model='nomic-embed-text-v1',
    task_type='search_document',
)

print(output)

This is using the 'nomic-embed-text-v1' weights. I want to use my custom fine-tuned weights trained using the contrastive fine-tuning method from this repository.

Is there a simple way to do that by specifying the path to the weights file?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions