Add pipeline tag, library name and license
#5
by
nielsr
HF Staff
- opened
README.md
CHANGED
|
@@ -1,3 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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).
|
|
@@ -12,7 +18,6 @@ model_name = "airkingbd/dplm_650m"
|
|
| 12 |
dplm = DiffusionProteinLanguageModel.from_pretrained(model_name)
|
| 13 |
```
|
| 14 |
|
| 15 |
-
|
| 16 |
All DPLM checkpoints are available in the table below:
|
| 17 |
| Model size | Num layers | Num parameters |
|
| 18 |
|------------------------------|----|----------|
|
|
@@ -20,5 +25,4 @@ All DPLM checkpoints are available in the table below:
|
|
| 20 |
| [dplm_650m](https://huggingface.co/airkingbd/dplm_650m) | 33 | 650M |
|
| 21 |
| [dplm_150m](https://huggingface.co/airkingbd/dplm_150m) | 30 | 150M |
|
| 22 |
|
| 23 |
-
|
| 24 |
**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 |
+
library_name: transformers
|
| 3 |
+
pipeline_tag: feature-extraction
|
| 4 |
+
license: apache-2.0
|
| 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).
|
|
|
|
| 18 |
dplm = DiffusionProteinLanguageModel.from_pretrained(model_name)
|
| 19 |
```
|
| 20 |
|
|
|
|
| 21 |
All DPLM checkpoints are available in the table below:
|
| 22 |
| Model size | Num layers | Num parameters |
|
| 23 |
|------------------------------|----|----------|
|
|
|
|
| 25 |
| [dplm_650m](https://huggingface.co/airkingbd/dplm_650m) | 33 | 650M |
|
| 26 |
| [dplm_150m](https://huggingface.co/airkingbd/dplm_150m) | 30 | 150M |
|
| 27 |
|
|
|
|
| 28 |
**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!
|