Model reference · open weights
bert-for-patents-64d is an open-weight embedding model from prithivida. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | prithivida |
|---|---|
| Type | Embedding models |
| Task | Embeddings |
| Context | 512 tokens |
| Runs with | transformers |
| Released | 2022-03-31 |
| Popularity | 510 downloads / month |
| Licence | Open weights |
About
This model is based on anferico/bert-for-patents - a BERTLARGE model (See next section for details below). By default, the pre-trained model's output embeddings with size 768 (base-models) or with size 1024 (large-models). However, when you store Millions of embeddings, this can require quite a lot of memory/storage. So have reduced the embedding dimension to 64 i.e 1/16th of 1024 using Principle Component Analysis (PCA) and it still gives a comparable performance. Yes! PCA gives better performance than NMF. Note: This process neither improves the runtime, nor the memory requirement for running the model. It only reduces the needed space to store embeddings, for example, for semantic search using vector databases.
BERT for Patents is a model trained by Google on 100M+ patents (not just US patents).
If you want to learn more about the model, check out the blog post, white paper and GitHub page containing the original TensorFlow checkpoint.
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys bert-for-patents-64d for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (bert-for-patents-64d below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/embeddings \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"bert-for-patents-64d","input":"text to embed"}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.