Ivysaur
Mihaiii/Ivysaur
published Apr 2024 · updated Apr 2024
Ivysaur is an embedding model fine-tuned on QA pairs for semantic-autocomplete.
specs
| Task | Text Embedding |
| Architecture | BERT |
| Parameters | 22.7M |
| Embedding Dimension | 384 |
| Max Sequence Length | 512 tokens |
about this model
Ivysaur is an embedding model fine-tuned from gte-tiny that produces 384-dimensional sentence embeddings, designed specifically for semantic-autocomplete applications.
The base model, gte-tiny (22.7M parameters), is distilled from gte-small and uses mean pooling with a maximum sequence length of 512 tokens. It follows the BERT architecture and offers performance comparable to its teacher at roughly half the model size. Ivysaur is further fine-tuned on the qa-assistant dataset (7.17k English question-answer pairs with relevance scores) using contrastive learning, which improves its ability to rank semantically similar query-response pairs for autocomplete suggestions.
Performance benchmarks
The teacher model gte-small achieves the following MTEB scores across 56 tasks (Ivysaur inherits similar quality with slightly reduced size):
| Task | Score |
|---|---|
| Clustering | 44.89 |
| Pair Classification | 83.54 |
| Reranking | 57.70 |
| Retrieval | 49.46 |
| STS | 82.07 |
| Summarization | 30.42 |
| Classification | 72.31 |
| Average | 61.36 |
Limitations
This model exclusively processes English text and truncates inputs longer than 512 tokens. It is released under the MIT license.
best for
- ·Semantic autocomplete suggestions
- ·QA pair retrieval and relevance scoring
- ·Semantic search over English text
FAQ
It is designed for semantic-autocomplete, where it suggests completions based on meaning rather than exact match.
Ivysaur is a fine-tune of gte-tiny on the qa-assistant dataset, improving performance on QA-like tasks while retaining the same 22.7M parameter size and 384-dimensional embeddings.
It accepts English text strings; long texts are truncated to 512 tokens. Use the sentence-transformers or HuggingFace Transformers library to generate embeddings.
Use the OpenAI-compatible endpoint with your API key and specify the model name "Mihaiii/Ivysaur" in your request.
We're benchmarking and onboarding Ivysaur as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.