Text Classification
Transformers
Safetensors
Russian
bert
icd10
medical
knowledge-distillation
text-embeddings-inference
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("Dmitry43243242/icd10-ru-chapter-distilled-alexyalunin-rubiobert")
model = AutoModelForSequenceClassification.from_pretrained("Dmitry43243242/icd10-ru-chapter-distilled-alexyalunin-rubiobert")Quick Links
ICD-10 Russian Chapter Distilled Student
Distilled student model for Russian ICD-10 chapter/group prediction.
- Student base model:
alexyalunin/RuBioBERT - Teacher source:
repo_ids - Teachers:
Dmitry43243242/icd10-ru-chapter-teacher-alexyalunin_rubiobert,Dmitry43243242/icd10-ru-chapter-teacher-alexyalunin_rubioroberta,Dmitry43243242/icd10-ru-chapter-teacher-ai_forever_rubert_base,Dmitry43243242/icd10-ru-chapter-teacher-cointegrated_rubert_tiny2,Dmitry43243242/icd10-ru-chapter-teacher-deeppavlov_rubert_base_cased - Selected KD run:
t2p0_hard0p5 - Temperature:
2.0 - Loss:
0.50 * CE + 0.50 * KL * T^2 - Class-weighted hard loss:
True
This is a decision-support model, not an automatic diagnosis system.
- Downloads last month
- 115
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Dmitry43243242/icd10-ru-chapter-distilled-alexyalunin-rubiobert")