aps6992 commited on
Commit
db1ca89
1 Parent(s): f65edc3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -10
README.md CHANGED
@@ -61,9 +61,9 @@ It builds on the work done in [SciRepEval: A Multi-Format Benchmark for Scientif
61
  - **Shared by :** Allen AI
62
  - **Model type:** bert-base-uncased + adapters
63
  - **License:** Apache 2.0
64
- - **Finetuned from model [optional]:** [allenai/scibert](https://huggingface.co/allenai/scibert_scivocab_uncased).
65
 
66
- ## Model Sources [optional]
67
 
68
  <!-- Provide the basic links for the model. -->
69
 
@@ -77,13 +77,14 @@ It builds on the work done in [SciRepEval: A Multi-Format Benchmark for Scientif
77
 
78
  ## Direct Use
79
 
80
- |Model|Type|Name and HF link|
81
  |--|--|--|
82
- |Base|Transformer|[allenai/specter2](https://huggingface.co/allenai/specter2)|
83
- |Classification|Adapter|[allenai/specter2_classification](https://huggingface.co/allenai/specter2_classification)|
84
- |Regression|Adapter|[allenai/specter2_regression](https://huggingface.co/allenai/specter2_regression)|
85
- |Retrieval|Adapter|[allenai/specter2_proximity](https://huggingface.co/allenai/specter2_proximity)|
86
- |Adhoc Query|Adapter|[allenai/specter2_adhoc_query](https://huggingface.co/allenai/specter2_adhoc_query)|
 
87
 
88
  ```python
89
  from transformers import AutoTokenizer, AutoModel
@@ -110,7 +111,7 @@ output = model(**inputs)
110
  embeddings = output.last_hidden_state[:, 0, :]
111
  ```
112
 
113
- ## Downstream Use [optional]
114
 
115
  <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
116
 
@@ -159,7 +160,6 @@ We also evaluate and establish a new SoTA on [MDCR](https://github.com/zoranmedi
159
  |[SPECTER](https://huggingface.co/allenai/specter)|54.7|57.4|68.0|(30.6, 25.5)|
160
  |[SciNCL](https://huggingface.co/malteos/scincl)|55.6|57.8|69.0|(32.6, 27.3)|
161
  |[SciRepEval-Adapters](https://huggingface.co/models?search=scirepeval)|61.9|59.0|70.9|(35.3, 29.6)|
162
- |[SPECTER 2.0-base](https://huggingface.co/allenai/specter2)|56.3|58.0|69.2|(38.0, 32.4)|
163
  |[SPECTER 2.0-Adapters](https://huggingface.co/models?search=allenai/specter-2)|**62.3**|**59.2**|**71.2**|**(38.4, 33.0)**|
164
 
165
  Please cite the following works if you end up using SPECTER 2.0:
 
61
  - **Shared by :** Allen AI
62
  - **Model type:** bert-base-uncased + adapters
63
  - **License:** Apache 2.0
64
+ - **Finetuned from model:** [allenai/scibert](https://huggingface.co/allenai/scibert_scivocab_uncased).
65
 
66
+ ## Model Sources
67
 
68
  <!-- Provide the basic links for the model. -->
69
 
 
77
 
78
  ## Direct Use
79
 
80
+ |Model|Name and HF link|Description|
81
  |--|--|--|
82
+ |Retrieval*|[allenai/specter2_proximity](https://huggingface.co/allenai/specter2_proximity)|Encode papers as queries and candidates eg. Link Prediction, Nearest Neighbor Search|
83
+ |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)|
84
+ |Classification|[allenai/specter2_classification](https://huggingface.co/allenai/specter2_classification)|Encode papers to feed into linear classifiers as features|
85
+ |Regression|[allenai/specter2_regression](https://huggingface.co/allenai/specter2_regression)|Encode papers to feed into linear regressors as features|
86
+
87
+ *Retrieval model should suffice for downstream task types not mentioned above
88
 
89
  ```python
90
  from transformers import AutoTokenizer, AutoModel
 
111
  embeddings = output.last_hidden_state[:, 0, :]
112
  ```
113
 
114
+ ## Downstream Use
115
 
116
  <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
117
 
 
160
  |[SPECTER](https://huggingface.co/allenai/specter)|54.7|57.4|68.0|(30.6, 25.5)|
161
  |[SciNCL](https://huggingface.co/malteos/scincl)|55.6|57.8|69.0|(32.6, 27.3)|
162
  |[SciRepEval-Adapters](https://huggingface.co/models?search=scirepeval)|61.9|59.0|70.9|(35.3, 29.6)|
 
163
  |[SPECTER 2.0-Adapters](https://huggingface.co/models?search=allenai/specter-2)|**62.3**|**59.2**|**71.2**|**(38.4, 33.0)**|
164
 
165
  Please cite the following works if you end up using SPECTER 2.0: