macadeliccc
commited on
Commit
•
0faa49d
1
Parent(s):
37ac50d
Update README.md
Browse files
README.md
CHANGED
@@ -62,6 +62,9 @@ GGUF versions are available [here](https://huggingface.co/macadeliccc/WestLake-7
|
|
62 |
|
63 |
## Chat Template
|
64 |
|
|
|
|
|
|
|
65 |
```python
|
66 |
def chatml_format(example):
|
67 |
# Format system
|
@@ -90,6 +93,8 @@ def chatml_format(example):
|
|
90 |
|
91 |
## Transformers
|
92 |
|
|
|
|
|
93 |
This demo code for the transformers library works properly:
|
94 |
|
95 |
```python
|
|
|
62 |
|
63 |
## Chat Template
|
64 |
|
65 |
+
This was my process during fine tune to realign the prompt template to chatML. There seems to be an error where you can use either Mistral (original) prompt template
|
66 |
+
or you can use ChatML in the GGUF version.
|
67 |
+
|
68 |
```python
|
69 |
def chatml_format(example):
|
70 |
# Format system
|
|
|
93 |
|
94 |
## Transformers
|
95 |
|
96 |
+
ChatML does not work properly in transformers for this model.
|
97 |
+
|
98 |
This demo code for the transformers library works properly:
|
99 |
|
100 |
```python
|