Update README.md
Browse files
README.md
CHANGED
|
@@ -76,13 +76,14 @@ It builds on the work done in [SciRepEval: A Multi-Format Benchmark for Scientif
|
|
| 76 |
|
| 77 |
## Direct Use
|
| 78 |
|
| 79 |
-
|Model|
|
| 80 |
|--|--|--|
|
| 81 |
-
|
|
| 82 |
-
|
|
| 83 |
-
|
|
| 84 |
-
|
|
| 85 |
-
|
|
|
|
| 86 |
|
| 87 |
```python
|
| 88 |
from transformers import AutoTokenizer, AutoModel
|
|
|
|
| 76 |
|
| 77 |
## Direct Use
|
| 78 |
|
| 79 |
+
|Model|Name and HF link|Description|
|
| 80 |
|--|--|--|
|
| 81 |
+
|Retrieval*|[allenai/specter2_proximity](https://huggingface.co/allenai/specter2_proximity)|Encode papers as queries and candidates eg. Link Prediction, Nearest Neighbor Search|
|
| 82 |
+
|Adhoc Query|[allenai/specter2_adhoc_query](https://huggingface.co/allenai/specter2_adhoc_query)|Encode short raw text queries for search tasks. (Candidate papers can be encoded with proximity)|
|
| 83 |
+
|Classification|[allenai/specter2_classification](https://huggingface.co/allenai/specter2_classification)|Encode papers to feed into linear classifiers as features|
|
| 84 |
+
|Regression|[allenai/specter2_regression](https://huggingface.co/allenai/specter2_regression)|Encode papers to feed into linear regressors as features|
|
| 85 |
+
|
| 86 |
+
*Retrieval model should suffice for downstream task types not mentioned above
|
| 87 |
|
| 88 |
```python
|
| 89 |
from transformers import AutoTokenizer, AutoModel
|