Text Ranking
sentence-transformers
Safetensors
convmemory
reranking
conversational-memory
cross-encoder
evidence-reranker
Instructions to use Purdy0228/ConvMemory-v2-Evidence-Reranker with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Purdy0228/ConvMemory-v2-Evidence-Reranker with sentence-transformers:
from sentence_transformers import CrossEncoder model = CrossEncoder("Purdy0228/ConvMemory-v2-Evidence-Reranker") query = "Which planet is known as the Red Planet?" passages = [ "Venus is often called Earth's twin because of its similar size and proximity.", "Mars, known for its reddish appearance, is often referred to as the Red Planet.", "Jupiter, the largest planet in our solar system, has a prominent red spot.", "Saturn, famous for its rings, is sometimes mistaken for the Red Planet." ] scores = model.predict([(query, passage) for passage in passages]) print(scores) - Notebooks
- Google Colab
- Kaggle
| { | |
| "candidate_pool": "ConvMemory v1 top10 from dense MPNet top500", | |
| "forbidden_inference_inputs": [ | |
| "gold", | |
| "gold_ids", | |
| "is_current", | |
| "is_latest", | |
| "is_stale", | |
| "stale", | |
| "answer", | |
| "answer_text", | |
| "ce_score", | |
| "mxbai_score", | |
| "teacher_score", | |
| "gpt_label", | |
| "entity_id", | |
| "slot_id" | |
| ], | |
| "format": "convmemory_evidence_reranker", | |
| "inference_inputs": [ | |
| "query text", | |
| "candidate memory text", | |
| "candidate id", | |
| "optional position/time metadata" | |
| ], | |
| "seed": 7, | |
| "source_experiment": "v361_top10_evidence_reranker.py", | |
| "teacher_weight": 0.0, | |
| "train_split": "LoCoMo dev split via choose_split(dev_ratio=0.5, seed=7)", | |
| "training_target": "gold-only listwise retrieval CE", | |
| "version": "0.5.0" | |
| } | |