Text Generation
PEFT
Safetensors
English
clinical
extraction
medical
qlora
lora
healthcare
on-prem
dilr
schema-agnostic
conversational
Instructions to use dilr/Mira-Q2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use dilr/Mira-Q2 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit") model = PeftModel.from_pretrained(base_model, "dilr/Mira-Q2") - Notebooks
- Google Colab
- Kaggle
| { | |
| "name": "mtsamples_282", | |
| "n": 282, | |
| "time_min": 63.1, | |
| "validity": { | |
| "point": 0.8582, | |
| "ci": [ | |
| 0.8191, | |
| 0.8972 | |
| ] | |
| }, | |
| "leak": { | |
| "point": 0.0, | |
| "ci": [ | |
| 0.0, | |
| 0.0 | |
| ] | |
| }, | |
| "type_distribution": { | |
| "medication_list": 26, | |
| "lab_report": 204, | |
| "PARSE_FAIL": 40, | |
| "physical_examination": 2, | |
| "donor_evaluation": 1, | |
| "discharge_summary": 6, | |
| "operating_note": 1, | |
| "procedure": 2 | |
| } | |
| } |