Update README.md
Browse files
README.md
CHANGED
@@ -42,10 +42,13 @@ These models were quantised using hardware kindly provided by [Latitude.sh](http
|
|
42 |
|
43 |
```
|
44 |
<|user|>
|
45 |
-
prompt
|
46 |
<|assistant|>
|
|
|
47 |
```
|
48 |
|
|
|
|
|
49 |
## Provided files
|
50 |
|
51 |
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
|
@@ -130,7 +133,7 @@ model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
|
|
130 |
|
131 |
prompt = "Tell me about AI"
|
132 |
prompt_template=f'''<|user|>
|
133 |
-
prompt
|
134 |
<|assistant|>
|
135 |
'''
|
136 |
|
|
|
42 |
|
43 |
```
|
44 |
<|user|>
|
45 |
+
{prompt}
|
46 |
<|assistant|>
|
47 |
+
|
48 |
```
|
49 |
|
50 |
+
Note: it is important to add a line break (`\n`) after the `<|assistant|>` token in the prompt template.
|
51 |
+
|
52 |
## Provided files
|
53 |
|
54 |
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
|
|
|
133 |
|
134 |
prompt = "Tell me about AI"
|
135 |
prompt_template=f'''<|user|>
|
136 |
+
{prompt}
|
137 |
<|assistant|>
|
138 |
'''
|
139 |
|