Downloads · 30 days
9
14% of all-time downloads
Med_scribe_V2
sahabajalam/Med_scribe_V2
Med_scribe_V2 is a machine learning model from sahabajalam. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
Fine-tuned LoRA adapter for MedGemma 1.5 4B-IT, specialized for generating clinical notes from doctor-patient conversations.
All-time downloads
64
Public
Repo size
97.8 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors59.8 MB · 60%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Feb 4, 2026
- Updated
- Feb 4, 2026
- SHA
- afb9b51a
Base models
Model card
From the Hugging Face model README
Med Scribe - Clinical Notes LoRA Adapter
Fine-tuned LoRA adapter for MedGemma 1.5 4B-IT, specialized for generating clinical notes from doctor-patient conversations.
Usage
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base_model = AutoModelForCausalLM.from_pretrained("google/medgemma-1.5-4b-it")
model = PeftModel.from_pretrained(base_model, "sahabajalam/Med_scribe")
tokenizer = AutoTokenizer.from_pretrained("google/medgemma-1.5-4b-it")
Training Details
- Base Model: google/medgemma-1.5-4b-it
- Method: QLoRA (4-bit quantization)
- LoRA rank: 16
- Training steps: 500
- Library
- peft
- License
- apache-2.0
- Created
- Feb 4, 2026
- Updated
- Feb 4, 2026