Edit model card

Model Card

🏆 Fine-Tuned Model from AI Talent Hub Hackathon

This model was fine-tuned during the AI Talent Hub Hackathon on a custom-generated dataset. The base model was fine-tuned to improve its performance on specific tasks related to "semantic search". It's second version of the model.

Model Details

Model Description

Train Dataset

34k - ['queries', 'corpus', 'relevant_docs', 'mode']

Split Info

chunk_size=512 chunk_overlap=20

  • Developed by: ianssens
  • Model type: text embedding
  • Language(s) (NLP): Russian
  • License: MIT
  • Finetuned from model [optional]: e5-large
Downloads last month
6
Safetensors
Model size
560M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.