Model reference · open weights
stackoverflow_mpnet is an open-weight embedding model from flax-sentence-embeddings. 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 | flax-sentence-embeddings |
|---|---|
| Type | Embedding models |
| Task | Embeddings |
| Context | 514 tokens |
| Runs with | sentence-transformers |
| Released | 2022-03-02 |
| Popularity | 520 downloads / month |
| Licence | Unknown |
About
This is a microsoft/mpnet-base model trained on 18,562,443 (title, body) pairs from StackOverflow.
SentenceTransformers is a set of models and frameworks that enable training and generating sentence embeddings from given data. The generated sentence embeddings can be utilized for Clustering, Semantic Search and other tasks. We used a pretrained microsoft/mpnet-base model and trained it using Siamese Network setup and contrastive learning objective. 18,562,443 (title, body) pairs from StackOverflow was used as training data. For this model, mean pooling of hidden states were used as sentence embeddings. See data_config.json and train_script.py in this respository how the model was trained and which datasets have been used.
We developed this model during the Community week using JAX/Flax for NLP & CV, organized by Hugging Face. We developed this model as part of the project: Train the Best Sentence Embedding Model Ever with 1B Training Pairs. We benefited from efficient hardware infrastructure to run the project: 7 TPUs v3-8, as well as assistance from Google’s Flax, JAX, and Cloud team members about efficient deep learning frameworks.
Our model is intended to be used as a sentence encoder for a search engine. Given an input sentence, it outputs a vector which captures the sentence semantic information. The sentence vector may be used for semantic-search, clustering or sentence similarity tasks.
Here is how to use this model to get the features of a given text using SentenceTransformers library:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer('flax-sentence-embeddings/stackoverflow_mpnet-base')
text = "Replace me by any question / answer you'd like."
text_embbedding = model.encode(text)
# array([-0.01559514, 0.04046123, 0.1317083 , 0.00085931, 0.04585106,
# -0.05607086, 0.0138078 , 0.03569756, 0.01420381, 0.04266302 ...],
# dtype=float32)
We use the pretrained microsoft/mpnet-base. Please refer to the model card for more detailed information about the pre-training procedure.
We fine-tune the model using a contrastive objective. Formally, we compute the cosine similarity from each possible sentence pairs from the batch. We then apply the cross entropy loss by comparing with true pairs.
We trained on model on a TPU v3-8. We train the model during 80k steps using a batch size of 1024 (128 per TPU core). We use a learning rate warm up of 500. The sequence length was limited to 128 tokens. We used the AdamW optimizer with a 2e-5 learning rate. The full training script is accessible in this current repository.
We used 18,562,443 (title, body) pairs from StackOverflow as training data.
| Dataset | Paper | Number of training tuples |
|---|---|---|
| StackOverflow title body pairs | - | 18,562,443 |
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys stackoverflow-mpnet for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (stackoverflow-mpnet 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":"stackoverflow-mpnet","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.