Update README.md
Browse files
README.md
CHANGED
|
@@ -9,11 +9,17 @@ datasets:
|
|
| 9 |
- allenai/scirepeval
|
| 10 |
---
|
| 11 |
|
| 12 |
-
|
| 13 |
|
| 14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
|
| 16 |
-
This adapter was created for usage with the **[adapters](https://github.com/adapter-hub/adapters)** library.
|
| 17 |
|
| 18 |
**Dec 2023 Update:**
|
| 19 |
|
|
@@ -31,17 +37,12 @@ Model usage updated to be compatible with latest versions of transformers and ad
|
|
| 31 |
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).
|
| 32 |
However, for benchmarking purposes, please continue using the current version.**
|
| 33 |
|
| 34 |
-
## SPECTER2
|
| 35 |
-
|
| 36 |
-
<!-- Provide a quick summary of what the model is/does. -->
|
| 37 |
|
| 38 |
-
|
| 39 |
-
This is the base model to be used along with the adapters.
|
| 40 |
-
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.
|
| 41 |
|
| 42 |
-
|
| 43 |
|
| 44 |
-
|
| 45 |
|
| 46 |
## Usage
|
| 47 |
|
|
|
|
| 9 |
- allenai/scirepeval
|
| 10 |
---
|
| 11 |
|
| 12 |
+
## SPECTER2
|
| 13 |
|
| 14 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 15 |
+
|
| 16 |
+
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_).
|
| 17 |
+
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.
|
| 18 |
+
|
| 19 |
+
**Note:For general embedding purposes, please use [allenai/specter2](https://huggingface.co/allenai/specter2).**
|
| 20 |
+
|
| 21 |
+
**To get the best performance on a downstream task type please load the associated adapter with the base model as in the example below.**
|
| 22 |
|
|
|
|
| 23 |
|
| 24 |
**Dec 2023 Update:**
|
| 25 |
|
|
|
|
| 37 |
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).
|
| 38 |
However, for benchmarking purposes, please continue using the current version.**
|
| 39 |
|
|
|
|
|
|
|
|
|
|
| 40 |
|
| 41 |
+
# Adapter `allenai/specter2_classification` for allenai/specter2_base
|
|
|
|
|
|
|
| 42 |
|
| 43 |
+
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.
|
| 44 |
|
| 45 |
+
This adapter was created for usage with the **[adapters](https://github.com/adapter-hub/adapters)** library.
|
| 46 |
|
| 47 |
## Usage
|
| 48 |
|