Update README.md
Browse files
README.md
CHANGED
|
@@ -34,22 +34,41 @@ adapter_name = model.load_adapter("allenai/specter2_adhoc_query", source="hf", s
|
|
| 34 |
|
| 35 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 36 |
|
| 37 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
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.
|
| 39 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
# Model Details
|
| 41 |
|
| 42 |
## Model Description
|
| 43 |
|
| 44 |
SPECTER 2.0 has been trained on over 6M triplets of scientific paper citations, which are available [here](https://huggingface.co/datasets/allenai/scirepeval/viewer/cite_prediction_new/evaluation).
|
| 45 |
-
Post that it is trained on all the [SciRepEval](https://huggingface.co/datasets/allenai/scirepeval) training tasks
|
| 46 |
|
| 47 |
Task Formats trained on:
|
| 48 |
- Classification
|
| 49 |
- Regression
|
| 50 |
-
- Proximity
|
| 51 |
- Adhoc Search
|
| 52 |
|
|
|
|
| 53 |
**This is the adhoc search query specific adapter. For tasks where papers have to retrieved for a short textual query, use this adapter to encode the query and [allenai/specter2_proximity](https://huggingface.co/allenai/specter2_proximity) to encode the candidates.**
|
| 54 |
|
| 55 |
|
|
@@ -79,12 +98,12 @@ It builds on the work done in [SciRepEval: A Multi-Format Benchmark for Scientif
|
|
| 79 |
|
| 80 |
|Model|Name and HF link|Description|
|
| 81 |
|--|--|--|
|
| 82 |
-
|
|
| 83 |
-
|Adhoc Query|[allenai/specter2_adhoc_query](https://huggingface.co/allenai/specter2_adhoc_query)|Encode short raw text queries for search tasks. (Candidate papers can be encoded with proximity)|
|
| 84 |
|Classification|[allenai/specter2_classification](https://huggingface.co/allenai/specter2_classification)|Encode papers to feed into linear classifiers as features|
|
| 85 |
|Regression|[allenai/specter2_regression](https://huggingface.co/allenai/specter2_regression)|Encode papers to feed into linear regressors as features|
|
| 86 |
|
| 87 |
-
*
|
| 88 |
|
| 89 |
```python
|
| 90 |
from transformers import AutoTokenizer, AutoModel
|
|
|
|
| 34 |
|
| 35 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 36 |
|
| 37 |
+
**Aug 2023 Update:**
|
| 38 |
+
1. The SPECTER 2.0 Base and proximity adapter models have been renamed in Hugging Face based upon usage patterns as follows:
|
| 39 |
+
|
| 40 |
+
|Old Name|New Name|
|
| 41 |
+
|--|--|
|
| 42 |
+
|allenai/specter2|[allenai/specter2_base](https://huggingface.co/allenai/specter2_base)|
|
| 43 |
+
|allenai/specter2_proximity|[allenai/specter2](https://huggingface.co/allenai/specter2)|
|
| 44 |
+
|
| 45 |
+
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).
|
| 46 |
+
However, for benchmarking purposes, please continue using the current version.
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
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_).
|
| 51 |
+
This is the base model to be used along with the adapters.
|
| 52 |
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.
|
| 53 |
|
| 54 |
+
**Note:For general embedding purposes, please use [allenai/specter2](https://huggingface.co/allenai/specter2).**
|
| 55 |
+
|
| 56 |
+
**To get the best performance on a downstream task type please load the associated adapter with the base model as in the example below.**
|
| 57 |
+
|
| 58 |
# Model Details
|
| 59 |
|
| 60 |
## Model Description
|
| 61 |
|
| 62 |
SPECTER 2.0 has been trained on over 6M triplets of scientific paper citations, which are available [here](https://huggingface.co/datasets/allenai/scirepeval/viewer/cite_prediction_new/evaluation).
|
| 63 |
+
Post that it is trained with additionally attached task format specific adapter modules on all the [SciRepEval](https://huggingface.co/datasets/allenai/scirepeval) training tasks.
|
| 64 |
|
| 65 |
Task Formats trained on:
|
| 66 |
- Classification
|
| 67 |
- Regression
|
| 68 |
+
- Proximity (Retrieval)
|
| 69 |
- Adhoc Search
|
| 70 |
|
| 71 |
+
|
| 72 |
**This is the adhoc search query specific adapter. For tasks where papers have to retrieved for a short textual query, use this adapter to encode the query and [allenai/specter2_proximity](https://huggingface.co/allenai/specter2_proximity) to encode the candidates.**
|
| 73 |
|
| 74 |
|
|
|
|
| 98 |
|
| 99 |
|Model|Name and HF link|Description|
|
| 100 |
|--|--|--|
|
| 101 |
+
|Proximity*|[allenai/specter2](https://huggingface.co/allenai/specter2)|Encode papers as queries and candidates eg. Link Prediction, Nearest Neighbor Search|
|
| 102 |
+
|Adhoc Query|[allenai/specter2_adhoc_query](https://huggingface.co/allenai/specter2_adhoc_query)|Encode short raw text queries for search tasks. (Candidate papers can be encoded with the proximity adapter)|
|
| 103 |
|Classification|[allenai/specter2_classification](https://huggingface.co/allenai/specter2_classification)|Encode papers to feed into linear classifiers as features|
|
| 104 |
|Regression|[allenai/specter2_regression](https://huggingface.co/allenai/specter2_regression)|Encode papers to feed into linear regressors as features|
|
| 105 |
|
| 106 |
+
*Proximity model should suffice for downstream task types not mentioned above
|
| 107 |
|
| 108 |
```python
|
| 109 |
from transformers import AutoTokenizer, AutoModel
|