Update README.md
Browse files
README.md
CHANGED
@@ -56,11 +56,12 @@ This GGUF is based on llama3-3-8B-Instruct thus ollama doesn't need anything els
|
|
56 |
After than you should be able to use this model to chat!
|
57 |
|
58 |
|
|
|
59 |
# NOTE: DISCLAIMER
|
60 |
|
61 |
Please note this is not for the purpose of production, but result of Fine Tuning through self learning
|
62 |
|
63 |
-
The llama3 Tokens where kept the same, however the format was slight customized using the available tokens
|
64 |
|
65 |
I have foregone the {{.System}} part as this would be updated when converting the llama3.
|
66 |
|
@@ -72,7 +73,7 @@ First pass through my ~30K personalized customized dataset.
|
|
72 |
If would like to know how I started creating my dataset, you can check this link
|
73 |
[Crafting GPT2 for Personalized AI-Preparing Data the Long Way (Part1)](https://medium.com/@deeokay/the-soul-in-the-machine-crafting-gpt2-for-personalized-ai-9d38be3f635f)
|
74 |
|
75 |
-
As the data was getting created with custom special tokens, I had to convert that to the llama3 Template.
|
76 |
|
77 |
However I got creative again.. the training data has the following Template:
|
78 |
|
|
|
56 |
After than you should be able to use this model to chat!
|
57 |
|
58 |
|
59 |
+
|
60 |
# NOTE: DISCLAIMER
|
61 |
|
62 |
Please note this is not for the purpose of production, but result of Fine Tuning through self learning
|
63 |
|
64 |
+
The llama3 Special Tokens where kept the same, however the format was slight customized using the available tokens
|
65 |
|
66 |
I have foregone the {{.System}} part as this would be updated when converting the llama3.
|
67 |
|
|
|
73 |
If would like to know how I started creating my dataset, you can check this link
|
74 |
[Crafting GPT2 for Personalized AI-Preparing Data the Long Way (Part1)](https://medium.com/@deeokay/the-soul-in-the-machine-crafting-gpt2-for-personalized-ai-9d38be3f635f)
|
75 |
|
76 |
+
As the data was getting created with custom GPT2 special tokens, I had to convert that to the llama3 Template.
|
77 |
|
78 |
However I got creative again.. the training data has the following Template:
|
79 |
|