Instructions to use InstalilyAI/synonym-transformer-3phase with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use InstalilyAI/synonym-transformer-3phase with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("InstalilyAI/synonym-transformer-3phase") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Automotive Parts Synonym Model
A fine-tuned SentenceTransformer model specialized for finding synonyms and related terms in automotive parts and service descriptions.
Model Description
This model is fine-tuned from sentence-transformers/all-MiniLM-L6-v2 specifically for automotive parts synonym detection. It can identify when different part names refer to the same or similar components.
Base Model: sentence-transformers/all-MiniLM-L6-v2
Training Details
Training Strategy: 3-phase approach
- Contextual Training (30 epochs): Full phrases with synonyms/antonyms
- Foundation Training (15 epochs): Word-to-word synonyms/antonyms
- Real-world Fine-tuning (4 epochs): Search phrases and repair descriptions
Loss Function: OnlineContrastiveLoss with varying margins (0.6 โ 0.4 โ 0.4)
Training Data: Automotive parts synonym/antonym pairs with contextual repair descriptions
Performance
Evaluated on 15-state synonyms phrases, deepseek general queries, STS-B and MTB datasets:
- Top-200 Synonym Recall 15251/15330 (99.5%)
- MRR@200 0.6454
- Top-200 Deepseek Recall 140633/142325 (98.8%)
- MRR@200 0.4401
- STS-B Spearman: 0.867
- MTB Spearman: 0.724
Limitations
- Optimized specifically for automotive parts and repair terminology
- May not perform well on general-domain text
- Downloads last month
- 1
Model tree for InstalilyAI/synonym-transformer-3phase
Base model
sentence-transformers/all-MiniLM-L6-v2