Update README.md
Browse files
README.md
CHANGED
|
@@ -4,4 +4,28 @@ datasets:
|
|
| 4 |
- timdettmers/openassistant-guanaco
|
| 5 |
---
|
| 6 |
|
| 7 |
-
This model is a test using Intel Gaudi Habana 2 chips using DDP training. Trained over 8xGaudi-2 Chips using DDP and Deepspeed using the openassistant dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
- timdettmers/openassistant-guanaco
|
| 5 |
---
|
| 6 |
|
| 7 |
+
This model is a test using Intel Gaudi Habana 2 chips using DDP training. Trained over 8xGaudi-2 Chips using DDP and Deepspeed using the openassistant dataset.
|
| 8 |
+
|
| 9 |
+
# Prompt Format
|
| 10 |
+
|
| 11 |
+
This model uses ChatML as the prompt format.
|
| 12 |
+
|
| 13 |
+
It's recommended to always prompt with a system instruction (use whatever system prompt you like):
|
| 14 |
+
|
| 15 |
+
```
|
| 16 |
+
<|im_start|>system
|
| 17 |
+
You are a helpful assistant for Python which outputs in Markdown format.<|im_end|>
|
| 18 |
+
<|im_start|>user
|
| 19 |
+
Write a function to calculate the Fibonacci sequence<|im_end|>
|
| 20 |
+
<|im_start|>assistant
|
| 21 |
+
|
| 22 |
+
```
|
| 23 |
+
|
| 24 |
+
For example, if you find the model's output to be overly verbose, instruct it to be short and concise:
|
| 25 |
+
|
| 26 |
+
```
|
| 27 |
+
<|im_start|>system
|
| 28 |
+
You are a helpful assistant. Be short and direct in your answers.<|im_end|>
|
| 29 |
+
<|im_start|>user
|
| 30 |
+
Was Tom Hanks in the movie Forrest Gump? If so, who did he play and give details of the plot.<|im_end|>
|
| 31 |
+
<|im_start|>assistan
|