Instructions to use Purdy0228/ConvMemory-OPC-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-OPC-V3-Validity-Context with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Purdy0228/ConvMemory-OPC-V3-Validity-Context") 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
Document ConvMemory 0.6.2 source integration
Browse files
README.md
CHANGED
|
@@ -42,6 +42,13 @@ scores = module.score_evidence_pairs([
|
|
| 42 |
])
|
| 43 |
```
|
| 44 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
## Selected Recipe
|
| 46 |
|
| 47 |
- Source experiment: `v632_opcos_v3_posrepeat8_checkpoint`
|
|
|
|
| 42 |
])
|
| 43 |
```
|
| 44 |
|
| 45 |
+
## Package Integration
|
| 46 |
+
|
| 47 |
+
Use `convmemory>=0.6.2` when attaching this checkpoint to `ConvMemory`. Pass
|
| 48 |
+
preselected later updates through `validity_source_map` to keep one validity
|
| 49 |
+
scorer call per protected target. Without a map, the package uses a bounded
|
| 50 |
+
Chinese-aware top-1 lexical fallback.
|
| 51 |
+
|
| 52 |
## Selected Recipe
|
| 53 |
|
| 54 |
- Source experiment: `v632_opcos_v3_posrepeat8_checkpoint`
|