Instructions to use jasperyeoh2/new-methodology-rerankers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use jasperyeoh2/new-methodology-rerankers with sentence-transformers:
from sentence_transformers import CrossEncoder model = CrossEncoder("jasperyeoh2/new-methodology-rerankers") 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
Add models README
Browse files
README.md
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: sentence-transformers
|
| 4 |
+
pipeline_tag: text-ranking
|
| 5 |
+
tags:
|
| 6 |
+
- cross-encoder
|
| 7 |
+
- reranker
|
| 8 |
+
- climate-fact-checking
|
| 9 |
+
- comp90042
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# New-Methodology finetuned rerankers
|
| 13 |
+
|
| 14 |
+
Cross-encoder / reranker checkpoints produced by `scripts/02_train_reranker.py` and related experiments.
|
| 15 |
+
|
| 16 |
+
## Subfolders
|
| 17 |
+
|
| 18 |
+
| HF path | Local source |
|
| 19 |
+
|---------|--------------|
|
| 20 |
+
| `finetuned_reranker/` | `outputs/retrieval/models/finetuned_reranker` |
|
| 21 |
+
| `ce_minilm_hybrid_hard_epochs2/` | `outputs/retrieval/models/ce_cross-encoder__ms-marco-MiniLM-L6-v2__hybrid_hard__epochs2` |
|
| 22 |
+
| `finetuned_bge_reranker/` | `outputs/retrieval/models/finetuned_bge_reranker` |
|
| 23 |
+
| `finetuned_minilm_hardneg/` | `outputs/retrieval/models/finetuned_minilm_hardneg` |
|
| 24 |
+
| `finetuned_reranker_s60/` | `outputs/retrieval/models/finetuned_reranker_s60` |
|
| 25 |
+
| `pairwise_reranker/` | `outputs/reranker/pairwise/pairwise_reranker` |
|
| 26 |
+
|
| 27 |
+
## Load example (sentence-transformers)
|
| 28 |
+
|
| 29 |
+
```python
|
| 30 |
+
from sentence_transformers import CrossEncoder
|
| 31 |
+
|
| 32 |
+
model = CrossEncoder("jasperyeoh2/new-methodology-rerankers", trust_remote_code=True)
|
| 33 |
+
# For a specific checkpoint, clone and point model_name_or_path to the subfolder.
|
| 34 |
+
```
|
| 35 |
+
|
| 36 |
+
## Recommended for MMR pipeline
|
| 37 |
+
|
| 38 |
+
Production MMR (位=0.5) uses **zero-shot** `cross-encoder/ms-marco-MiniLM-L6-v2`, not these finetuned weights.
|
| 39 |
+
Finetuned checkpoints are kept for reproducibility and ablation.
|