StableGalen-6b / README.md
baebee's picture
Update README.md
3587495
metadata
license: other
datasets:
  - Photolens/MedText-DoctorLLaMa-OpenOrca-formatted
  - shibing624/medical
language:
  - en
tags:
  - medicine
  - doctor

This model is the DeciLM-6b-Instruct model, trained specifically for medicine

Galen uses the

### User: {prompt}

### Response:

or

{prompt} 

Prompt templates

Galen Training Recipe:

  • target_modules = ["q_proj", "v_proj", "gate_proj", "down_proj", "up_proj", "k_proj", "o_proj"]
  • Learning Rate: 4e-4
  • LR Scheduler: constant
  • 250 StepsLoss

T3: 1 Hour