Add pipeline tag, link to project page, correct paper link
Browse filesThis PR adds the `pipeline_tag: text-generation` to the model card metadata, linking the project page, and correcting the paper link to the Hugging Face Papers link.
README.md
CHANGED
@@ -1,12 +1,13 @@
|
|
1 |
---
|
2 |
-
library_name: transformers
|
3 |
-
license: apache-2.0
|
4 |
-
language:
|
5 |
-
- en
|
6 |
datasets:
|
7 |
- Skylion007/openwebtext
|
|
|
|
|
|
|
|
|
8 |
metrics:
|
9 |
- perplexity
|
|
|
10 |
---
|
11 |
|
12 |
## Using MDLM
|
@@ -28,9 +29,7 @@ was trained using a forward diffusion process that generates inputs varying from
|
|
28 |
reconstruct the original input from these varying levels of masking, outputting logits in the process.
|
29 |
The training regimen comprised one million steps on the OpenWebText corpus, involving the processing of a total of `33 billion` tokens.
|
30 |
|
31 |
-
For more details, please see our paper: [Simple and Effective Masked Diffusion Language Models](
|
32 |
-
|
33 |
-
|
34 |
|
35 |
## Citation
|
36 |
|
|
|
1 |
---
|
|
|
|
|
|
|
|
|
2 |
datasets:
|
3 |
- Skylion007/openwebtext
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
library_name: transformers
|
7 |
+
license: apache-2.0
|
8 |
metrics:
|
9 |
- perplexity
|
10 |
+
pipeline_tag: text-generation
|
11 |
---
|
12 |
|
13 |
## Using MDLM
|
|
|
29 |
reconstruct the original input from these varying levels of masking, outputting logits in the process.
|
30 |
The training regimen comprised one million steps on the OpenWebText corpus, involving the processing of a total of `33 billion` tokens.
|
31 |
|
32 |
+
For more details, please see our paper: [Simple and Effective Masked Diffusion Language Models](https://huggingface.co/papers/2406.07524).
|
|
|
|
|
33 |
|
34 |
## Citation
|
35 |
|