README.md
| 1 | --- |
| 2 | license: mit |
| 3 | pipeline_tag: sentence-similarity |
| 4 | --- |
| 5 | |
| 6 | Quantized ONNX port of [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) for text classification and similarity searches. |
| 7 | |
| 8 | ### Usage |
| 9 | |
| 10 | Here's an example of performing inference using the model with [FastEmbed](https://github.com/qdrant/fastembed). |
| 11 | |
| 12 | ```py |
| 13 | from fastembed import TextEmbedding |
| 14 | |
| 15 | documents = [ |
| 16 | "You should stay, study and sprint.", |
| 17 | "History can only prepare us to be surprised yet again.", |
| 18 | ] |
| 19 | |
| 20 | model = TextEmbedding(model_name="BAAI/bge-small-en-v1.5") |
| 21 | embeddings = list(model.embed(documents)) |
| 22 | |
| 23 | # [ |
| 24 | # array([ |
| 25 | # 0.00611658, 0.00068912, -0.0203846, ..., -0.01751488, -0.01174267, |
| 26 | # 0.01463472 |
| 27 | # ], |
| 28 | # dtype=float32), |
| 29 | # array([ |
| 30 | # 0.00173448, -0.00329958, 0.01557874, ..., -0.01473586, 0.0281806, |
| 31 | # -0.00448205 |
| 32 | # ], |
| 33 | # dtype=float32) |
| 34 | # ] |
| 35 | ``` |