Update README.md
Browse files
README.md
CHANGED
|
@@ -55,15 +55,6 @@ When using the model, make sure your prompt is formated correctly!
|
|
| 55 |
|
| 56 |
Also, we recommend using VLLM rather than Hugging Face.
|
| 57 |
|
| 58 |
-
## Prompt Format:
|
| 59 |
-
|
| 60 |
-
```python
|
| 61 |
-
chat_template = "{% for message in messages %}{% if message['role'] == 'assistant' %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}<start_of_turn>{{ role }}\n{{ message['content'] | trim }}<end_of_turn>\n{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}"
|
| 62 |
-
with_system_prompt = "<start_of_turn>system\nYou are a helpful assistant.<end_of_turn>\n<start_of_turn>user\nTranslate: Hello, world! into Portuguese.<end_of_turn>\n"
|
| 63 |
-
# System prompts are optional.
|
| 64 |
-
without_system_prompt = "<start_of_turn>user\nTranslate: Hello, world! into Portuguese.<end_of_turn>\n"
|
| 65 |
-
```
|
| 66 |
-
|
| 67 |
### Using on VLLM:
|
| 68 |
|
| 69 |
```python
|
|
|
|
| 55 |
|
| 56 |
Also, we recommend using VLLM rather than Hugging Face.
|
| 57 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
### Using on VLLM:
|
| 59 |
|
| 60 |
```python
|