Sentence Similarity
sentence-transformers
Safetensors
English
bert
keyphrase-ranking
text-embeddings-inference
Instructions to use sabsab129/MiniLM-searchkeys with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use sabsab129/MiniLM-searchkeys with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("sabsab129/MiniLM-searchkeys") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
| { | |
| "batch_json": "batch_0.json", | |
| "datasets": [ | |
| "kp20k.jsonl", | |
| "kptimes.jsonl", | |
| "kpbiomed.jsonl" | |
| ], | |
| "model_name": "sentence-transformers/all-MiniLM-L12-v2", | |
| "output_base": "finetuned_model", | |
| "n_batches": 10000, | |
| "epochs": 10, | |
| "loss_mode": "mulsupcon", | |
| "temperature": 0.05, | |
| "lr": 0.00001, | |
| "warmup_ratio": 0.1, | |
| "max_grad_norm": 1.0, | |
| "weight_decay": 0.01, | |
| "max_seq_len": 512, | |
| "chunk": 96, | |
| "min_chunk": 4, | |
| "vram_gb": null, | |
| "grad_checkpointing": false, | |
| "empty_cache": true, | |
| "drop_percentage": 0.0, | |
| "hold_percentage": 0.0, | |
| "drop_method": "random", | |
| "kp_sampling": "random", | |
| "seed": 42, | |
| "log_every": 5, | |
| "deterministic": false, | |
| "clean_local_epochs": true, | |
| "run_name": null, | |
| "resume_path": null, | |
| "no_resume": false, | |
| "force": false | |
| } |