Adapters
bert
aps6992 commited on
Commit
d813e97
1 Parent(s): b643247

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -5
README.md CHANGED
@@ -8,6 +8,10 @@ datasets:
8
 
9
  # Adapter `allenai/specter2` for allenai/specter2_base
10
 
 
 
 
 
11
  **Aug 2023 Update:**
12
  1. **The SPECTER 2.0 Base and proximity adapter models have been renamed in Hugging Face based upon usage patterns as follows:**
13
 
@@ -19,11 +23,6 @@ datasets:
19
  2. **We have a parallel version (termed [aug2023refresh](https://huggingface.co/allenai/specter2_aug2023refresh)) where the base transformer encoder version is pre-trained on a collection of newer papers (published after 2018).
20
  However, for benchmarking purposes, please continue using the current version.**
21
 
22
-
23
- An [adapter](https://adapterhub.ml) for the [allenai/specter2_base](https://huggingface.co/allenai/specter2_base) model that was trained on the [allenai/scirepeval](https://huggingface.co/datasets/allenai/scirepeval/) dataset.
24
-
25
- This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
26
-
27
  ## SPECTER 2.0
28
 
29
  <!-- Provide a quick summary of what the model is/does. -->
 
8
 
9
  # Adapter `allenai/specter2` for allenai/specter2_base
10
 
11
+ An [adapter](https://adapterhub.ml) for the [allenai/specter2_base](https://huggingface.co/allenai/specter2_base) model that was trained on the [allenai/scirepeval](https://huggingface.co/datasets/allenai/scirepeval/) dataset.
12
+
13
+ This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
14
+
15
  **Aug 2023 Update:**
16
  1. **The SPECTER 2.0 Base and proximity adapter models have been renamed in Hugging Face based upon usage patterns as follows:**
17
 
 
23
  2. **We have a parallel version (termed [aug2023refresh](https://huggingface.co/allenai/specter2_aug2023refresh)) where the base transformer encoder version is pre-trained on a collection of newer papers (published after 2018).
24
  However, for benchmarking purposes, please continue using the current version.**
25
 
 
 
 
 
 
26
  ## SPECTER 2.0
27
 
28
  <!-- Provide a quick summary of what the model is/does. -->