BAAI/bge-reranker-v2-m3
Rank documents against a query with BAAI/bge-reranker-v2-m3, a multilingual reranker with 568M parameters and an 8k-token context length.
BAAI/bge-reranker-v2-m3 is a multilingual reranker model with 568 million parameters. It reads a query and a set of texts, and returns a relevance score for each text against that query. AI Inference runs it under the id baai-bge-reranker-v2-m3.
Model details
The model id is the string a call passes to select this model. The HuggingFace repository holds the model card.
| Detail | Value |
|---|---|
| Model name | BAAI/bge-reranker-v2-m3 |
| Version | Original |
| Model category | Reranker |
| Model id | baai-bge-reranker-v2-m3 |
| Size | 568M parameters |
| HuggingFace model | BAAI/bge-reranker-v2-m3 |
| License | Apache 2.0 |
Capabilities
These values describe the model itself and are not fields of the request body. For the fields a reranking request carries, and their types, refer to Model invocation.
| Capability | Value |
|---|---|
| Input data | Text |
| Context length | 8k tokens |
| Supports LoRA | No |
Usage
A function calls the model with Azion.AI.run, passing the id as the first argument and the request body as the second. This model takes no messages array: each of the two operations below has its own body. To send the same body over HTTP instead, refer to Model invocation.
Reranking
A reranking request carries the query and the documents to rank against it:
The model returns a results array ordered from the highest relevance_score to the lowest, one entry per document, each carrying the position the document held in the request and its text:
Scoring
A scoring request carries text_1 and the text_2 array the model scores against it:
The response carries the same results array, with one entry and one relevance_score for every text in text_2.