Sentence Similarity
sentence-transformers
Safetensors
German
English
multilingual
xlm-roberta
feature-extraction
retrieval
semantic-search
ifc
lca
text-embeddings-inference
Instructions to use Hygroskopisch/bge-m3-ifc-kbob-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Hygroskopisch/bge-m3-ifc-kbob-finetuned with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Hygroskopisch/bge-m3-ifc-kbob-finetuned") sentences = [ "Das ist eine glückliche Person", "Das ist ein glücklicher Hund", "Das ist eine sehr glückliche Person", "Heute ist ein sonniger Tag" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
| { | |
| "run_id": "generated_queries-mapping_generated_querie-bge-m3-e2-b32-lr2e-05-d0p1-s42-d1-f8c0ccef", | |
| "rule_hash": "88814a6f2add361886c1919c0904b93a7afd0152", | |
| "train_file": "Training/outputs/phase12/random_preselected_pairs_generated_queries-mapping_generated_querie-bge-m3-e2-b32-lr2e-05-d0p1-s42-d1-f8c0ccef.jsonl", | |
| "base_model": "BAAI/bge-m3", | |
| "output_dir": "models/Hygroskopisch/new/model", | |
| "prefix_mode": "no_prefix", | |
| "source_of_prefix_setting": "dense_only_bge_m3_default", | |
| "dense_only_bge_m3_default_applied": true, | |
| "legacy_prefix_experiment_active": false, | |
| "device": "cuda", | |
| "epochs": 2, | |
| "batch_size": 32, | |
| "learning_rate": 2e-05, | |
| "warmup_ratio": 0.1, | |
| "max_length": 128, | |
| "dev_ratio": 0.1, | |
| "seed": 42, | |
| "fp16": true, | |
| "hard_negative_mode": "fallback", | |
| "hard_negative_selection": "random_preselected", | |
| "num_hard_negatives": 2, | |
| "model_selection_metric": "hit5_mrr10", | |
| "hard_negative_stats": { | |
| "records_total": 14748, | |
| "dropped_non_positive_weight": 0, | |
| "records_after_mode": 14748, | |
| "records_with_hard_negatives": 14748, | |
| "examples_total": 29496, | |
| "examples_per_record_avg": 2.0, | |
| "dropped_no_hard_negatives": 0, | |
| "fallback_negatives_used": 0, | |
| "fallback_fill_count": 0, | |
| "dropped_unusable": 0, | |
| "use_hard_negatives": 1, | |
| "num_hard_negatives_requested": 2, | |
| "renormalized_weight_applied": 14748, | |
| "preselected_used": 29496, | |
| "preselected_used_count": 29496, | |
| "preselected_missing_runtime_fallback": 0, | |
| "preselected_conflicts_with_positives": 0 | |
| }, | |
| "sampler_mode": "UniquePositiveBatchSampler", | |
| "sampler_query_positive_union_aware": true, | |
| "train_queries_with_multiple_positives": 3226, | |
| "save_each_epoch": false, | |
| "steps_per_epoch": 7418, | |
| "total_pairs": 16386, | |
| "train_pairs": 14748, | |
| "dev_pairs": 1638, | |
| "epoch_checkpoints": [] | |
| } |