Instructions to use aydin237/medbrain-squad-scribe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use aydin237/medbrain-squad-scribe with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("google/medgemma-1.5-4b-it") model = PeftModel.from_pretrained(base_model, "aydin237/medbrain-squad-scribe") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -28,7 +28,7 @@ clinical documentation.
|
|
| 28 |
- **Base model:** google/medgemma-1.5-4b-it
|
| 29 |
- **Method:** LoRA (Rank 16, Alpha 32)
|
| 30 |
- **Dataset:** 500-row Teacher-Student distillation dataset
|
| 31 |
-
(Gemini 3.0
|
| 32 |
- **Hardware:** Dual NVIDIA T4 (Kaggle)
|
| 33 |
- **Framework:** HuggingFace PEFT + TRL
|
| 34 |
|
|
|
|
| 28 |
- **Base model:** google/medgemma-1.5-4b-it
|
| 29 |
- **Method:** LoRA (Rank 16, Alpha 32)
|
| 30 |
- **Dataset:** 500-row Teacher-Student distillation dataset
|
| 31 |
+
(Gemini 3.0 Pro teacher → MedGemma student)
|
| 32 |
- **Hardware:** Dual NVIDIA T4 (Kaggle)
|
| 33 |
- **Framework:** HuggingFace PEFT + TRL
|
| 34 |
|