Text Classification
Transformers
Safetensors
PEFT
English
distilbert
medical-triage
lora
healthcare
symptom-checker
natural-language-processing
academic-project
Eval Results (legacy)
text-embeddings-inference
Instructions to use cristian-untaru/lora-distilbert-medical-triage with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cristian-untaru/lora-distilbert-medical-triage with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="cristian-untaru/lora-distilbert-medical-triage")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("cristian-untaru/lora-distilbert-medical-triage") model = AutoModelForSequenceClassification.from_pretrained("cristian-untaru/lora-distilbert-medical-triage", device_map="auto") - PEFT
How to use cristian-untaru/lora-distilbert-medical-triage with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
| { | |
| "base_model": "distilbert-base-uncased", | |
| "adaptation_method": "LoRA", | |
| "peft_type": "LORA", | |
| "lora_rank": 16, | |
| "lora_alpha": 32, | |
| "lora_dropout": 0.1, | |
| "target_modules": [ | |
| "q_lin", | |
| "v_lin" | |
| ], | |
| "modules_to_save": [ | |
| "pre_classifier", | |
| "classifier" | |
| ], | |
| "num_labels": 3, | |
| "max_length": 128, | |
| "num_train_epochs": 8, | |
| "learning_rate": 0.0002, | |
| "batch_size_train": 16, | |
| "batch_size_eval": 32, | |
| "weight_decay": 0.01, | |
| "warmup_ratio": 0.1, | |
| "fp16": true, | |
| "early_stopping_patience": 3, | |
| "metric_for_best_model": "f1", | |
| "train_size": 490, | |
| "validation_size": 105, | |
| "test_size": 106, | |
| "hf_repo_id": "cristian-untaru/lora-distilbert-medical-triage" | |
| } |