Text Ranking
sentence-transformers
Safetensors
convmemory
memory
agent-memory
validity
reranking
cross-encoder
Instructions to use Purdy0228/ConvMemory-v3-Validity-Context with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Purdy0228/ConvMemory-v3-Validity-Context with sentence-transformers:
from sentence_transformers import CrossEncoder model = CrossEncoder("Purdy0228/ConvMemory-v3-Validity-Context") 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
Document ConvMemory 0.6.2 source integration
Browse files
README.md
CHANGED
|
@@ -98,6 +98,14 @@ The package exposes two scoring paths:
|
|
| 98 |
The second path is the preferred dense-workload path because it avoids per-pair
|
| 99 |
CrossEncoder calls.
|
| 100 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 101 |
## Method-Level Evaluation
|
| 102 |
|
| 103 |
The v511 5-seed Memora-retrieval benchmark is the method-level estimate. It
|
|
|
|
| 98 |
The second path is the preferred dense-workload path because it avoids per-pair
|
| 99 |
CrossEncoder calls.
|
| 100 |
|
| 101 |
+
## Package Integration
|
| 102 |
+
|
| 103 |
+
Use `convmemory>=0.6.2` for the bounded integrated source-selection path.
|
| 104 |
+
Applications with an update index can pass one selected source per target with
|
| 105 |
+
`validity_source_map`; otherwise the package uses a bounded top-1 lexical
|
| 106 |
+
fallback over the protected result prefix. The package does not run an
|
| 107 |
+
unbounded all-pairs CrossEncoder search.
|
| 108 |
+
|
| 109 |
## Method-Level Evaluation
|
| 110 |
|
| 111 |
The v511 5-seed Memora-retrieval benchmark is the method-level estimate. It
|