Update README.md
Browse files
README.md
CHANGED
@@ -47,7 +47,7 @@ If would like to know how I started creating my dataset, you can check this link
|
|
47 |
|
48 |
As the data was getting created with custom special tokens, I had to convert that to the llama3 Template.
|
49 |
|
50 |
-
However I got creative again..
|
51 |
|
52 |
```python
|
53 |
<|begin_of_text|> <|start_header_id|>user<|end_header_id|>
|
@@ -58,6 +58,7 @@ However I got creative again..
|
|
58 |
{{.Sentiment}}<|eot_id|> <|start_header_id|>user<|end_header_id|>
|
59 |
Thank you for your answer.<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
60 |
You're most welcome, what would like to know next?<|eot_id|>
|
|
|
61 |
```
|
62 |
|
63 |
For now, the llama3 standard template seems to hold, and can be created in Ollama through normal llama3 template
|
|
|
47 |
|
48 |
As the data was getting created with custom special tokens, I had to convert that to the llama3 Template.
|
49 |
|
50 |
+
However I got creative again.. the training data has the following Template:
|
51 |
|
52 |
```python
|
53 |
<|begin_of_text|> <|start_header_id|>user<|end_header_id|>
|
|
|
58 |
{{.Sentiment}}<|eot_id|> <|start_header_id|>user<|end_header_id|>
|
59 |
Thank you for your answer.<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
60 |
You're most welcome, what would like to know next?<|eot_id|>
|
61 |
+
|
62 |
```
|
63 |
|
64 |
For now, the llama3 standard template seems to hold, and can be created in Ollama through normal llama3 template
|