Update README.md
Browse files
README.md
CHANGED
|
@@ -67,7 +67,9 @@ A small 101M param (total) decoder model. This is the first version of the model
|
|
| 67 |
- GQA (24 heads, 8 key-value), context length 1024
|
| 68 |
- train-from-scratch
|
| 69 |
|
| 70 |
-
|
|
|
|
|
|
|
| 71 |
|
| 72 |
---
|
| 73 |
|
|
|
|
| 67 |
- GQA (24 heads, 8 key-value), context length 1024
|
| 68 |
- train-from-scratch
|
| 69 |
|
| 70 |
+
**This model** is the 'raw' pretrained model and has not been fine-tuned on a more specific task. **it should be fine-tuned further before using for most use-cases**.
|
| 71 |
+
|
| 72 |
+
- For the chat version of this model, please [see here](https://youtu.be/dQw4w9WgXcQ?si=3ePIqrY1dw94KMu4)
|
| 73 |
|
| 74 |
---
|
| 75 |
|