Update README.md
Browse files
README.md
CHANGED
|
@@ -54,6 +54,21 @@ https://AlignmentLab.ai
|
|
| 54 |
|
| 55 |
We used [OpenAI's Chat Markup Language (ChatML)](https://github.com/openai/openai-python/blob/main/chatml.md) format, with `<|im_start|>` and `<|im_end|>` tokens added to support this.
|
| 56 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
# Evaluation
|
| 58 |
|
| 59 |
We have evaluated using the methodology and tools for the HuggingFace Leaderboard, and find that we have significantly improved upon the base long context model.
|
|
|
|
| 54 |
|
| 55 |
We used [OpenAI's Chat Markup Language (ChatML)](https://github.com/openai/openai-python/blob/main/chatml.md) format, with `<|im_start|>` and `<|im_end|>` tokens added to support this.
|
| 56 |
|
| 57 |
+
## Example Prompt Exchange
|
| 58 |
+
|
| 59 |
+
```
|
| 60 |
+
<|im_start|>system
|
| 61 |
+
You are LlongOrca, a large language model trained by Alignment Lab AI. Write out your reasoning step-by-step to be sure you get the right answers!
|
| 62 |
+
<|im_end|>
|
| 63 |
+
<|im_start|>user
|
| 64 |
+
How are you<|im_end|>
|
| 65 |
+
<|im_start|>assistant
|
| 66 |
+
I am doing well!<|im_end|>
|
| 67 |
+
<|im_start|>user
|
| 68 |
+
How are you now?<|im_end|>
|
| 69 |
+
```
|
| 70 |
+
|
| 71 |
+
|
| 72 |
# Evaluation
|
| 73 |
|
| 74 |
We have evaluated using the methodology and tools for the HuggingFace Leaderboard, and find that we have significantly improved upon the base long context model.
|