Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,31 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: bigscience-openrail-m
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
tags:
|
| 5 |
+
- pytorch
|
| 6 |
+
- causal-lm
|
| 7 |
license: bigscience-openrail-m
|
| 8 |
---
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
GeoV-9B is a 20 billion parameter autoregressive language model
|
| 12 |
+
|
| 13 |
+
### Model details
|
| 14 |
+
|
| 15 |
+
- Developed by: [Georges Harik](http://twitter.com/gharik)
|
| 16 |
+
- Model type: Transformer-based Language Model
|
| 17 |
+
- Language: English
|
| 18 |
+
|
| 19 |
+
<figure style="width:30em">
|
| 20 |
+
|
| 21 |
+
| Hyperparameter | Value |
|
| 22 |
+
| ---------------------- | ----------- |
|
| 23 |
+
| n<sub>parameters</sub> | 9B |
|
| 24 |
+
| n<sub>layers</sub> | 32 |
|
| 25 |
+
| d<sub>model</sub> | 5120 |
|
| 26 |
+
| n<sub>heads</sub> | 40 |
|
| 27 |
+
| d<sub>head</sub> | 128 |
|
| 28 |
+
| n<sub>vocab</sub> | 65500 |
|
| 29 |
+
| Sequence Length | 2049 |
|
| 30 |
+
</figure>
|
| 31 |
+
|