aps6992 commited on
Commit
a38cc12
1 Parent(s): 2c7a46c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -12
README.md CHANGED
@@ -6,11 +6,16 @@ datasets:
6
  - allenai/scirepeval
7
  ---
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 **[adapters](https://github.com/adapter-hub/adapters)** library.
 
 
 
 
 
14
 
15
  **Dec 2023 Update:**
16
 
@@ -27,17 +32,11 @@ Model usage updated to be compatible with latest versions of transformers and ad
27
  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).
28
  However, for benchmarking purposes, please continue using the current version.**
29
 
30
- ## SPECTER2
31
-
32
- <!-- Provide a quick summary of what the model is/does. -->
33
-
34
- 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_).
35
- This is the base model to be used along with the adapters.
36
- 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.
37
 
38
- **Note:For general embedding purposes, please use [allenai/specter2](https://huggingface.co/allenai/specter2).**
39
 
40
- **To get the best performance on a downstream task type please load the associated adapter with the base model as in the example below.**
41
 
42
 
43
  ## Usage
 
6
  - allenai/scirepeval
7
  ---
8
 
9
+ ## SPECTER2
10
 
11
+ <!-- Provide a quick summary of what the model is/does. -->
12
 
13
+ 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_).
14
+ 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.
15
+
16
+ **Note:For general embedding purposes, please use [allenai/specter2](https://huggingface.co/allenai/specter2).**
17
+
18
+ **To get the best performance on a downstream task type please load the associated adapter () with the base model as in the example below.**
19
 
20
  **Dec 2023 Update:**
21
 
 
32
  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).
33
  However, for benchmarking purposes, please continue using the current version.**
34
 
35
+ # Adapter `allenai/specter2` for allenai/specter2_base
 
 
 
 
 
 
36
 
37
+ 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.
38
 
39
+ This adapter was created for usage with the **[adapters](https://github.com/adapter-hub/adapters)** library.
40
 
41
 
42
  ## Usage