Commit
•
7e169e4
1
Parent(s):
cbb162a
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,35 @@
|
|
1 |
---
|
2 |
-
license:
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
+
pipeline_tag: text-generation
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
tags:
|
7 |
+
- pretrained
|
8 |
---
|
9 |
+
|
10 |
+
# Model Card for Mistral-DNA-v0.1
|
11 |
+
|
12 |
+
The Mistral-DNA-v0.1 Large Language Model (LLM) is a pretrained generative DNA text model with 164K parameters x 64 experts = 105M parameters.
|
13 |
+
It is derived from Mistral-7B-v0.1 model, which was simplified for DNA: the number of layers and the hidden size were reduced.
|
14 |
+
This version v0.1 of Mistral-DNA corresponds to a pretty simple model, which was primarly designed low computational resources (the aim was not to get the best accuracy results).
|
15 |
+
|
16 |
+
For full details of this model please read our Blog [release blog post](xxx).
|
17 |
+
|
18 |
+
## Model Architecture
|
19 |
+
|
20 |
+
Like Mistral-7B-v0.1, it is a transformer model, with the following architecture choices:
|
21 |
+
- Grouped-Query Attention
|
22 |
+
- Sliding-Window Attention
|
23 |
+
- Byte-fallback BPE tokenizer
|
24 |
+
|
25 |
+
## Troubleshooting
|
26 |
+
|
27 |
+
Ensure you are utilizing a stable version of Transformers, 4.34.0 or newer.
|
28 |
+
|
29 |
+
## Notice
|
30 |
+
|
31 |
+
Mistral-DNA is a pretrained base model for DNA.
|
32 |
+
|
33 |
+
## Contact
|
34 |
+
|
35 |
+
Raphaël Mourad. raphael.mourad@univ-tlse3.fr
|