doctolib-lab/doctosae-bge-large-en-v1.5

https://huggingface.co/doctolib-lab/doctosae-bge-large-en-v1.5
Activeby doctolib-lab03updated 5 days ago

Sparse autoencoders (SAEs) trained on BAAI/bge-large-en-v1.5 embeddings for medical retrieval, from the paper Explanations that Transfer: Interpreting Medical Retrieval with Sparse AutoEncoders (ML4H 2026). Code: doctolib-lab/doctosae.

Sourced from

  • HuggingFace — doctolib-lab/doctosae-bge-large-en-v1.5

Related resources

Sparse autoencoders (SAEs) trained on abhinand/MedEmbed-large-v0.1 embeddings for medical retrieval, from the paper Explanations that Transfer: Interpreting Medical Retrieval with Sparse AutoEncoders (ML4H 2026). Code: doctolib-lab/doctosae.

Active05 days ago

> Requires the Google Gemini API. These SAEs take gemini-embedding-001 embeddings as input. That model is proprietary and only available through the paid Gemini API or Vertex AI; no weights are distributed with this repository.

Active05 days ago

# Adapting LLMs to Domains via Continual Pre-Training (ICLR 2024) This repo contains the domain-specific base model developed from LLaMA-1-7B, using the method in our paper Adapting Large Language Models via Reading Comprehension.

Idle2331 year ago
Python

# FremyCompany/BioLORD-2023-M This model was trained using BioLORD, a new pre-training strategy for producing meaningful representations for clinical sentences and biomedical concepts.

Idle37.1K1 year ago
Python

A frontier protein-language generative model — because proteins deserve better small talk.

Idle102.3K7 months ago

Model Size: 8B (English)

Idle561 year ago