aps6992 commited on
Commit
177b1cc
1 Parent(s): 1fb33ce

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -6
README.md CHANGED
@@ -4,21 +4,27 @@ datasets:
4
  - allenai/scirepeval
5
  ---
6
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  **Dec 2023 Update:**
8
 
9
  Model usage updated to be compatible with latest versions of transformers and adapters (newly released update to adapter-transformers) libraries.
10
 
11
-
12
  **\*\*\*\*\*\*Update\*\*\*\*\*\***
13
 
14
  This update introduces a new set of SPECTER2 models with the base transformer encoder pre-trained on an extended citation dataset containing more recent papers.
15
  For benchmarking purposes please use the existing SPECTER2 [models](https://huggingface.co/allenai/specter2) w/o the **aug2023refresh** suffix.
16
 
17
- # SPECTER2 (Base)
18
- SPECTER2 is the successor to [SPECTER](https://huggingface.co/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_).
19
- This is the base model to be used along with the adapters.
20
- 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.
21
-
22
  **Note:For general embedding purposes, please use [allenai/specter2](https://huggingface.co/allenai/specter2).**
23
 
24
  **To get the best performance on a downstream task type please load the associated adapter with the base model as in the example below.**
 
4
  - allenai/scirepeval
5
  ---
6
 
7
+ ## SPECTER2
8
+
9
+ <!-- Provide a quick summary of what the model is/does. -->
10
+
11
+ SPECTER2 is a family of models that succeeds [SPECTER](https://huggingface.co/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_).
12
+ This is the base encoder to be used with relevant task specific adapters.
13
+ 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.
14
+
15
+ **Note:For general embedding purposes, please use [allenai/specter2](https://huggingface.co/allenai/specter2).**
16
+
17
+ **To get the best performance on a downstream task type please load the associated adapter () with the base model as in the example below.**
18
+
19
  **Dec 2023 Update:**
20
 
21
  Model usage updated to be compatible with latest versions of transformers and adapters (newly released update to adapter-transformers) libraries.
22
 
 
23
  **\*\*\*\*\*\*Update\*\*\*\*\*\***
24
 
25
  This update introduces a new set of SPECTER2 models with the base transformer encoder pre-trained on an extended citation dataset containing more recent papers.
26
  For benchmarking purposes please use the existing SPECTER2 [models](https://huggingface.co/allenai/specter2) w/o the **aug2023refresh** suffix.
27
 
 
 
 
 
 
28
  **Note:For general embedding purposes, please use [allenai/specter2](https://huggingface.co/allenai/specter2).**
29
 
30
  **To get the best performance on a downstream task type please load the associated adapter with the base model as in the example below.**