Fill-Mask
Transformers
Safetensors
roformer
biology
medical
ideasbyjin commited on
Commit
544125f
·
2 Parent(s): c21e312e263b5c

Merge branch 'main' of https://huggingface.co/alchemab/antiberta2

Browse files
Files changed (1) hide show
  1. README.md +8 -5
README.md CHANGED
@@ -1,22 +1,25 @@
1
  ---
2
  license: other
3
  widget:
4
- - text: "Ḣ Q V Q [MASK] E"
 
 
 
5
  ---
6
 
7
  ## AntiBERTa2 🧬
8
 
9
  AntiBERTa2 is an antibody-specific language model based on the [RoFormer model](https://arxiv.org/abs/2104.09864) - it is pre-trained using masked language modelling.
10
  We also provide a multimodal version of AntiBERTa2, AntiBERTa2-CSSP, that has been trained using a contrastive objective, similar to the [CLIP method](https://arxiv.org/abs/2103.00020).
11
- Further details on both AntiBERTa2 and AntiBERTa2-CSSP are described in our [paper]() accepted at the NeurIPS MLSB Workshop 2023.
12
 
13
  Both AntiBERTa2 models are only available for non-commercial use. Output antibody sequences (e.g. from infilling via masked language models) can only be used for
14
  non-commercial use. For any users seeking commercial use of our model and generated antibodies, please reach out to us at [info@alchemab.com](mailto:info@alchemab.com).
15
 
16
  | Model variant | Parameters | Config |
17
  | ------------- | ---------- | ------ |
18
- | [AntiBERTa2](https://huggingface.co/alchemab/antiberta2) | 202M | 24L, 12H, 1024d |
19
- | [AntiBERTa2-CSSP](https://huggingface.co/alchemab/antiberta2-cssp) | 202M | 24L, 12H, 1024d |
20
 
21
  ## Example usage
22
 
@@ -38,4 +41,4 @@ non-commercial use. For any users seeking commercial use of our model and genera
38
  # that a new linear layer will be added
39
  # and randomly initialized
40
 
41
- ```
 
1
  ---
2
  license: other
3
  widget:
4
+ - text: Ḣ Q V Q [MASK] E
5
+ tags:
6
+ - biology
7
+ - medical
8
  ---
9
 
10
  ## AntiBERTa2 🧬
11
 
12
  AntiBERTa2 is an antibody-specific language model based on the [RoFormer model](https://arxiv.org/abs/2104.09864) - it is pre-trained using masked language modelling.
13
  We also provide a multimodal version of AntiBERTa2, AntiBERTa2-CSSP, that has been trained using a contrastive objective, similar to the [CLIP method](https://arxiv.org/abs/2103.00020).
14
+ Further details on both AntiBERTa2 and AntiBERTa2-CSSP are described in our [paper](https://www.mlsb.io/papers_2023/Enhancing_Antibody_Language_Models_with_Structural_Information.pdf) accepted at the NeurIPS MLSB Workshop 2023.
15
 
16
  Both AntiBERTa2 models are only available for non-commercial use. Output antibody sequences (e.g. from infilling via masked language models) can only be used for
17
  non-commercial use. For any users seeking commercial use of our model and generated antibodies, please reach out to us at [info@alchemab.com](mailto:info@alchemab.com).
18
 
19
  | Model variant | Parameters | Config |
20
  | ------------- | ---------- | ------ |
21
+ | [AntiBERTa2](https://huggingface.co/alchemab/antiberta2) | 202M | 16L, 16H, 1024d |
22
+ | [AntiBERTa2-CSSP](https://huggingface.co/alchemab/antiberta2-cssp) | 202M | 16L, 16H, 1024d |
23
 
24
  ## Example usage
25
 
 
41
  # that a new linear layer will be added
42
  # and randomly initialized
43
 
44
+ ```