Update README.md
Browse files
README.md
CHANGED
@@ -20,7 +20,17 @@ GGUF [llama.cpp](https://github.com/ggerganov/llama.cpp) quantized version of:
|
|
20 |
- [License](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/blob/main/LICENSE)
|
21 |
|
22 |
## Recommended Prompt Format (Llama3)
|
23 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
|
25 |
---
|
26 |
|
|
|
20 |
- [License](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/blob/main/LICENSE)
|
21 |
|
22 |
## Recommended Prompt Format (Llama3)
|
23 |
+
```
|
24 |
+
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
25 |
+
|
26 |
+
Provide some context and/or instructions to the model.<|eot_id|>
|
27 |
+
<|start_header_id|>assistant<|end_header_id|>
|
28 |
+
|
29 |
+
The user’s message goes here<|eot_id|>
|
30 |
+
<|start_header_id|>assistant<|end_header_id|>
|
31 |
+
|
32 |
+
AI message goes here<|eot_id|>
|
33 |
+
```
|
34 |
|
35 |
---
|
36 |
|