Instructions to use openbmb/MiniCPM-Reranker with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openbmb/MiniCPM-Reranker with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="openbmb/MiniCPM-Reranker", trust_remote_code=True)# Load model directly from transformers import AutoModelForSequenceClassification model = AutoModelForSequenceClassification.from_pretrained("openbmb/MiniCPM-Reranker", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -160,7 +160,7 @@ We re-rank top-100 docments from `bge-large-zh-v1.5` in C-MTEB/Retrieval and fro
|
|
| 160 |
|
| 161 |
We re-rank top-100 documents from `bge-m3` (Dense).
|
| 162 |
|
| 163 |
-
| 模型 Model | MKQA
|
| 164 |
|------------------------------------|--------------------|--------------------|--------------------|
|
| 165 |
| bge-m3 (Dense)(Retriever) | 66.4 | 30.49 | 41.09 |
|
| 166 |
| jina-reranker-v2-base-multilingual | 69.33 | 36.66 | 50.03 |
|
|
|
|
| 160 |
|
| 161 |
We re-rank top-100 documents from `bge-m3` (Dense).
|
| 162 |
|
| 163 |
+
| 模型 Model | MKQA En-Zh_CN (Recall@20) | NeuCLIR22 (NDCG@10) | NeuCLIR23 (NDCG@10) |
|
| 164 |
|------------------------------------|--------------------|--------------------|--------------------|
|
| 165 |
| bge-m3 (Dense)(Retriever) | 66.4 | 30.49 | 41.09 |
|
| 166 |
| jina-reranker-v2-base-multilingual | 69.33 | 36.66 | 50.03 |
|