Update README.md
Browse files
README.md
CHANGED
@@ -9,10 +9,21 @@ tags:
|
|
9 |
- gpt
|
10 |
widget:
|
11 |
- text: "Where is Zurich? Ans:"
|
12 |
-
- text: "
|
13 |
---
|
14 |
|
15 |
-
#
|
16 |
|
|
|
|
|
|
|
17 |
|
|
|
18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
- gpt
|
10 |
widget:
|
11 |
- text: "Where is Zurich? Ans:"
|
12 |
+
- text: "What is the highest mountain? Answer:"
|
13 |
---
|
14 |
|
15 |
+
# Model Summary
|
16 |
|
17 |
+
We present Together-GPT-J-6B-ProxAdam-50x, capable of following human instructions and conduct zero/few-shot inference.
|
18 |
+
The model trained in a decentralized fashion with ProxAdam optimizer, requiring only 2% cross-machine communication compared to vanilla data parallel training.
|
19 |
+
We fine-tune GPT-J-6B on NI, P3, COT, the pile data.
|
20 |
|
21 |
+
# Quick Start
|
22 |
|
23 |
+
```python
|
24 |
+
from transformers import pipeline
|
25 |
+
|
26 |
+
pipe = pipeline(model='togethercomputer/Together-gpt-J-6B-ProxAdam-50x')
|
27 |
+
|
28 |
+
pipe("Where is Zurich? Ans:")
|
29 |
+
```
|