aps6992 commited on
Commit
b643247
1 Parent(s): 4952134

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +18 -24
README.md CHANGED
@@ -8,18 +8,35 @@ datasets:
8
 
9
  # Adapter `allenai/specter2` for allenai/specter2_base
10
 
11
- **Aug 2023 Update: The SPECTER 2.0 base and proximity adapter models have been renamed in Hugging Face based upon usage patterns as follows:**
 
12
 
13
  |Old Name|New Name|
14
  |--|--|
15
  |allenai/specter2|[allenai/specter2_base](https://huggingface.co/allenai/specter2_base)|
16
  |allenai/specter2_proximity|[allenai/specter2](https://huggingface.co/allenai/specter2)|
17
 
 
 
 
18
 
19
  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.
20
 
21
  This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
22
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  ## Usage
24
 
25
  First, install `adapter-transformers`:
@@ -37,30 +54,7 @@ from transformers import AutoAdapterModel
37
  model = AutoAdapterModel.from_pretrained("allenai/specter2_base")
38
  adapter_name = model.load_adapter("allenai/specter2", source="hf", set_active=True)
39
  ```
40
- ## SPECTER 2.0
41
-
42
- <!-- Provide a quick summary of what the model is/does. -->
43
 
44
- **Aug 2023 Update:**
45
- 1. The SPECTER 2.0 Base and proximity adapter models have been renamed in Hugging Face based upon usage patterns as follows:
46
-
47
- |Old Name|New Name|
48
- |--|--|
49
- |allenai/specter2|[allenai/specter2_base](https://huggingface.co/allenai/specter2_base)|
50
- |allenai/specter2_proximity|[allenai/specter2](https://huggingface.co/allenai/specter2)|
51
-
52
- 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).
53
- However, for benchmarking purposes, please continue using the current version.
54
-
55
-
56
-
57
- SPECTER 2.0 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_).
58
- This is the base model to be used along with the adapters.
59
- 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.
60
-
61
- **Note:For general embedding purposes, please use [allenai/specter2](https://huggingface.co/allenai/specter2).**
62
-
63
- **To get the best performance on a downstream task type please load the associated adapter with the base model as in the example below.**
64
 
65
  # Model Details
66
 
 
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
 
14
  |Old Name|New Name|
15
  |--|--|
16
  |allenai/specter2|[allenai/specter2_base](https://huggingface.co/allenai/specter2_base)|
17
  |allenai/specter2_proximity|[allenai/specter2](https://huggingface.co/allenai/specter2)|
18
 
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. -->
30
+
31
+ SPECTER 2.0 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_).
32
+ This is the base model to be used along with the adapters.
33
+ 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.
34
+
35
+ **Note:For general embedding purposes, please use [allenai/specter2](https://huggingface.co/allenai/specter2).**
36
+
37
+ **To get the best performance on a downstream task type please load the associated adapter with the base model as in the example below.**
38
+
39
+
40
  ## Usage
41
 
42
  First, install `adapter-transformers`:
 
54
  model = AutoAdapterModel.from_pretrained("allenai/specter2_base")
55
  adapter_name = model.load_adapter("allenai/specter2", source="hf", set_active=True)
56
  ```
 
 
 
57
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
 
59
  # Model Details
60