Instructions to use geoffsee/octen-embedding-0.6b-onnx-int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use geoffsee/octen-embedding-0.6b-onnx-int4 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("geoffsee/octen-embedding-0.6b-onnx-int4") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
| { | |
| "model_id": "Octen/Octen-Embedding-0.6B", | |
| "opset": 18, | |
| "max_seq_length": 512, | |
| "export_mode": "direct_fp16", | |
| "export_batch_size": 4, | |
| "dynamic_batch": true, | |
| "device": "mps", | |
| "pooling": "last_token", | |
| "normalize": "l2", | |
| "padding_side": "left", | |
| "weights_dtype": "float16", | |
| "output_dtype": "float32", | |
| "hidden_size": 1024, | |
| "files": { | |
| "onnx_fp16": "model.fp16.onnx", | |
| "tokenizer_dir": "tokenizer" | |
| } | |
| } | |