shivendrra
commited on
Commit
•
01ea1ce
1
Parent(s):
e9e5531
Update README.md
Browse files
README.md
CHANGED
@@ -21,16 +21,16 @@ It also has one more BERT based model that has 47million parameters, also capabl
|
|
21 |
### Model Description
|
22 |
|
23 |
- **Developed by:** [Shivendra Singh]()
|
24 |
-
- **License:**
|
25 |
|
26 |
### Model Sources
|
27 |
|
28 |
- **Repository:** [github/enigma-1.5b](https://github.com/shivendrra/enigma-1.5b)
|
29 |
-
- **Papers**: [
|
30 |
|
31 |
## Uses
|
32 |
|
33 |
-
Can be used to generate new sequences of DNA on a given input of tokens. Or can be used for further research. Anyway, it's very basic in nature.
|
34 |
### Direct Use
|
35 |
|
36 |
Load the model and then can be used to generate new sequences, `max_length=512` for 2.5b model and `256` for enbert-47m model.
|
|
|
21 |
### Model Description
|
22 |
|
23 |
- **Developed by:** [Shivendra Singh]()
|
24 |
+
- **License:** MIT
|
25 |
|
26 |
### Model Sources
|
27 |
|
28 |
- **Repository:** [github/enigma-1.5b](https://github.com/shivendrra/enigma-1.5b)
|
29 |
+
- **Papers**: [Understanding the Natural Language of DNA using Encoder-Decoder Foundation Models with Byte-level Precision](https://arxiv.org/html/2311.02333v2#bib.bib35
|
30 |
|
31 |
## Uses
|
32 |
|
33 |
+
Can be used to generate new sequences of DNA on a given input of tokens. Or can be used for further research. Anyway, it's very basic in nature. I'll add more functionalities which includes classification of dna, masked token generation, etc. Maybe even implement MOE techinque in future.
|
34 |
### Direct Use
|
35 |
|
36 |
Load the model and then can be used to generate new sequences, `max_length=512` for 2.5b model and `256` for enbert-47m model.
|