Prompt template
Browse files
README.md
CHANGED
@@ -41,7 +41,7 @@ output = model.generate(
|
|
41 |
response = tokenizer.decode(output[context_length:], skip_special_tokens=True)
|
42 |
print(response)
|
43 |
```
|
44 |
-
Please ahere to the prompt template: `<<SYS>>\n{
|
45 |
|
46 |
License: [Llama-3.1 License](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B/blob/main/LICENSE)
|
47 |
|
|
|
41 |
response = tokenizer.decode(output[context_length:], skip_special_tokens=True)
|
42 |
print(response)
|
43 |
```
|
44 |
+
Please ahere to the prompt template (system prompt is optional): `<<SYS>>\n{system prompt}\n<</SYS>>\n\n[INST]{query1}[/INST]{response1}[INST]{query2}[/INST]{response2}...`
|
45 |
|
46 |
License: [Llama-3.1 License](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B/blob/main/LICENSE)
|
47 |
|