Add library name, pipeline tag and license

#5
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +10 -1
README.md CHANGED
@@ -1,7 +1,15 @@
 
 
 
 
 
 
1
  # DPLM
2
  DPLM (diffusion protein language model) is a versatile protein language model that demonstrates strong generative and predictive capabilities for protein sequences. Specifically, DPLM exhibits impressive performance in protein sequence generation, motif scaffolding, inverse folding, and representation learning.
3
  For more detailed information about DPLM, please refer to our paper [Diffusion Language Models Are Versatile Protein Learners](https://arxiv.org/abs/2402.18567).
4
 
 
 
5
  This repository contains the DPLM model checkpoint of 150M parameters.
6
  Please refer to our [github repository](https://github.com/bytedance/dplm/tree/main) for code and usage.
7
  For example, you can load DPLM model as below:
@@ -11,7 +19,6 @@ model_name = "airkingbd/dplm_150m"
11
  dplm = DiffusionProteinLanguageModel.from_pretrained(model_name)
12
  ```
13
 
14
-
15
  All DPLM checkpoints are available in the table below:
16
  | Model size | Num layers | Num parameters |
17
  |------------------------------|----|----------|
@@ -19,5 +26,7 @@ All DPLM checkpoints are available in the table below:
19
  | [dplm_650m](https://huggingface.co/airkingbd/dplm_650m) | 33 | 650M |
20
  | [dplm_150m](https://huggingface.co/airkingbd/dplm_150m) | 30 | 150M |
21
 
 
 
22
 
23
  **News**: welcome to check our new work [DPLM-2: A Multimodal Diffusion Protein Language Model](https://huggingface.co/papers/2410.13782), a multimodal protein foundation model that extends DPLM to simultaneously model, understand, and generate both sequences and structures!
 
1
+ ---
2
+ license: apache-2.0
3
+ pipeline_tag: feature-extraction
4
+ library_name: transformers
5
+ ---
6
+
7
  # DPLM
8
  DPLM (diffusion protein language model) is a versatile protein language model that demonstrates strong generative and predictive capabilities for protein sequences. Specifically, DPLM exhibits impressive performance in protein sequence generation, motif scaffolding, inverse folding, and representation learning.
9
  For more detailed information about DPLM, please refer to our paper [Diffusion Language Models Are Versatile Protein Learners](https://arxiv.org/abs/2402.18567).
10
 
11
+ Project Page: https://bytedance.github.io/dplm/dplm-2.1
12
+
13
  This repository contains the DPLM model checkpoint of 150M parameters.
14
  Please refer to our [github repository](https://github.com/bytedance/dplm/tree/main) for code and usage.
15
  For example, you can load DPLM model as below:
 
19
  dplm = DiffusionProteinLanguageModel.from_pretrained(model_name)
20
  ```
21
 
 
22
  All DPLM checkpoints are available in the table below:
23
  | Model size | Num layers | Num parameters |
24
  |------------------------------|----|----------|
 
26
  | [dplm_650m](https://huggingface.co/airkingbd/dplm_650m) | 33 | 650M |
27
  | [dplm_150m](https://huggingface.co/airkingbd/dplm_150m) | 30 | 150M |
28
 
29
+ For details regarding the design space of multimodal protein language models (MPLMs), please refer to our spotlight paper at ICML'25:
30
+ [Elucidating the Design Space of Multimodal Protein Language Models](https://huggingface.co/papers/2504.11454)
31
 
32
  **News**: welcome to check our new work [DPLM-2: A Multimodal Diffusion Protein Language Model](https://huggingface.co/papers/2410.13782), a multimodal protein foundation model that extends DPLM to simultaneously model, understand, and generate both sequences and structures!