Update README.md
Browse files
README.md
CHANGED
@@ -34,6 +34,16 @@ We recommend **dequantising the model before merging**, as done in [this script]
|
|
34 |
- **Repository:** https://github.com/allenai/https://github.com/allenai/open-instruct
|
35 |
- **Model Family:** Other models and the dataset are found in the [Tulu V2 collection](https://huggingface.co/collections/allenai/tulu-v2-suite-6551b56e743e6349aab45101).
|
36 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
37 |
|
38 |
## Intended uses & limitations
|
39 |
|
|
|
34 |
- **Repository:** https://github.com/allenai/https://github.com/allenai/open-instruct
|
35 |
- **Model Family:** Other models and the dataset are found in the [Tulu V2 collection](https://huggingface.co/collections/allenai/tulu-v2-suite-6551b56e743e6349aab45101).
|
36 |
|
37 |
+
## Input Format
|
38 |
+
|
39 |
+
The model is trained to use the following format (note the newlines):
|
40 |
+
```
|
41 |
+
<|user|>
|
42 |
+
Your message here!
|
43 |
+
<|assistant|>
|
44 |
+
```
|
45 |
+
|
46 |
+
For best results, format all inputs in this manner. **Make sure to include a newline after `<|assistant|>`, this can affect generation quality quite a bit.**
|
47 |
|
48 |
## Intended uses & limitations
|
49 |
|