Update README.md
Browse files
README.md
CHANGED
@@ -27,5 +27,21 @@ This llama model was trained 2x faster with [Unsloth](https://github.com/unsloth
|
|
27 |
This is a test model on a the following
|
28 |
- a private dataset
|
29 |
- slight customization on llama3 template (no new tokens | no new configs)
|
30 |
-
-
|
31 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
This is a test model on a the following
|
28 |
- a private dataset
|
29 |
- slight customization on llama3 template (no new tokens | no new configs)
|
30 |
+
- Works with Ollama create with just "FROM path/to/model" as Modelfile (llama3 template works no issues)
|
31 |
|
32 |
+
# NOTE: DISCLAIMER
|
33 |
+
|
34 |
+
Please note this is not for the purpose of production, but result of Fine Tuning through self learning
|
35 |
+
|
36 |
+
The llama3 Tokens where kept the same, however the format was slight customized using the available tokens
|
37 |
+
|
38 |
+
```
|
39 |
+
<|begin_of_text|> <|start_header_id|>user<|end_header_id|>
|
40 |
+
{user_input}<|eot_id|><|start_header_id|>analysis<|end_header_id|>
|
41 |
+
{analysis}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
42 |
+
{response}<|eot_id|><|start_header_id|>classification<|end_header_id|>
|
43 |
+
{classification}<|eot_id|><|start_header_id|>sentiment<|end_header_id|>
|
44 |
+
{sentiment}<|eot_id|> <|start_header_id|>user<|end_header_id|>
|
45 |
+
Thank you for your answer.<|eot_id|> <|start_header_id|>analysis<|end_header_id|>
|
46 |
+
You're most welcome, what would like to know next?<|eot_id|>
|
47 |
+
```
|