Update README.md

README.md

@@ -11,6 +11,7 @@ language:
 
 SPECTER 2.0 is the successor to [SPECTER](allenai/specter) and is capable of generating task specific embeddings for scientific tasks when paired with [adapters](https://huggingface.co/models?search=allenai/specter-2_).
 Given the combination of title and abstract of a scientific paper or a short texual query, the model can be used to generate effective embeddings to be used in downstream applications.
+**Note:** To get the best performance on a downstream task type please load the associated adapter with the base model as [below]()
 
 # Model Details
 
@@ -50,13 +51,14 @@ It builds on the work done in [SciRepEval: A Multi-Format Benchmark for Scientif
 
 ## Direct Use
 
-|Model|Type|Name and HF link|
+|Model|Name and HF link|Description|
 |--|--|--|
-|Base|Transformer|[allenai/specter2](https://huggingface.co/allenai/specter2)|
-|Classification|Adapter|[allenai/specter2_classification](https://huggingface.co/allenai/specter2_classification)|
-|Regression|Adapter|[allenai/specter2_regression](https://huggingface.co/allenai/specter2_regression)|
-|Retrieval|Adapter|[allenai/specter2_proximity](https://huggingface.co/allenai/specter2_proximity)|
-|Adhoc Query|Adapter|[allenai/specter2_adhoc_query](https://huggingface.co/allenai/specter2_adhoc_query)|
+|Retrieval*|[allenai/specter2_proximity](https://huggingface.co/allenai/specter2_proximity)|Encode papers as queries and candidates eg. Link Prediction, Nearest Neighbor Search|
+|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)|
+|Classification|[allenai/specter2_classification](https://huggingface.co/allenai/specter2_classification)|Encode papers to feed into linear classifiers as features|
+|Regression|[allenai/specter2_regression](https://huggingface.co/allenai/specter2_regression)|Encode papers to feed into linear regressors as features|
+
+*Retrieval model should suffice for downstream task types not mentioned above
 
 ```python
 from transformers import AutoTokenizer, AutoModel
@@ -68,7 +70,8 @@ tokenizer = AutoTokenizer.from_pretrained('allenai/specter2')
 model = AutoModel.from_pretrained('allenai/specter2')
 
 #load the adapter(s) as per the required task, provide an identifier for the adapter in load_as argument and activate it
-model.load_adapter("allenai/specter2_adhoc_query", source="hf", load_as="adhoc_query", set_active=True)
+model.load_adapter("allenai/specter2_proximity", source="hf", load_as="proximity", set_active=True)
+#other possibilities: allenai/specter2_<classification|regression|adhoc_query>
 
 papers = [{'title': 'BERT', 'abstract': 'We introduce a new language representation model called BERT'},
           {'title': 'Attention is all you need', 'abstract': ' The dominant sequence transduction models are based on complex recurrent or convolutional neural networks'}]
@@ -83,7 +86,7 @@ output = model(**inputs)
 embeddings = output.last_hidden_state[:, 0, :]
 ```
 
-## Downstream Use [optional]
+## Downstream Use
 
 <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
 
@@ -132,7 +135,6 @@ We also evaluate and establish a new SoTA on [MDCR](https://github.com/zoranmedi
 |[SPECTER](https://huggingface.co/allenai/specter)|54.7|57.4|68.0|(30.6, 25.5)|
 |[SciNCL](https://huggingface.co/malteos/scincl)|55.6|57.8|69.0|(32.6, 27.3)|
 |[SciRepEval-Adapters](https://huggingface.co/models?search=scirepeval)|61.9|59.0|70.9|(35.3, 29.6)|
-|[SPECTER 2.0-base](https://huggingface.co/allenai/specter2)|56.3|58.0|69.2|(38.0, 32.4)|
 |[SPECTER 2.0-Adapters](https://huggingface.co/models?search=allenai/specter-2)|**62.3**|**59.2**|**71.2**|**(38.4, 33.0)**|
 
 Please cite the following works if you end up using SPECTER 2.0: