kamalkraj/e5-mistral-7b-instruct

Finetune mistral-7b-instruct for sentence embeddings

44
/ 100
Emerging

This project helps machine learning engineers or researchers adapt a large language model (Mistral-7B-Instruct) to create highly accurate sentence embeddings for specific needs. It takes an existing model and a dataset of text pairs and outputs a fine-tuned model capable of generating better numerical representations of sentences. The target user is someone developing advanced natural language processing applications, like semantic search or text similarity.

No commits in the last 6 months.

Use this if you need to improve the quality of sentence embeddings from a Mistral-7B-Instruct model for a particular text domain or application.

Not ideal if you are not comfortable with machine learning model training, as it requires setting up and running a fine-tuning pipeline.

natural-language-processing machine-learning-engineering semantic-search information-retrieval text-similarity
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

88

Forks

19

Language

Python

License

Apache-2.0

Last pushed

May 02, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/kamalkraj/e5-mistral-7b-instruct"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.