Commit
•
d8a54e1
1
Parent(s):
c027bd5
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,9 @@ model_link: https://huggingface.co/jarradh/llama2_70b_chat_uncensored
|
|
| 14 |
model_type: llama
|
| 15 |
quantized_by: TheBloke
|
| 16 |
base_model: jarradh/llama2_70b_chat_uncensored
|
|
|
|
|
|
|
|
|
|
| 17 |
---
|
| 18 |
|
| 19 |
<!-- header start -->
|
|
@@ -317,4 +320,4 @@ model_output_dir: models/ # model saved in {model_output_dir}/{model_name}
|
|
| 317 |
```
|
| 318 |
|
| 319 |
# Fine-tuning guide
|
| 320 |
-
https://georgesung.github.io/ai/qlora-ift/
|
|
|
|
| 14 |
model_type: llama
|
| 15 |
quantized_by: TheBloke
|
| 16 |
base_model: jarradh/llama2_70b_chat_uncensored
|
| 17 |
+
language:
|
| 18 |
+
- en
|
| 19 |
+
- bg
|
| 20 |
---
|
| 21 |
|
| 22 |
<!-- header start -->
|
|
|
|
| 320 |
```
|
| 321 |
|
| 322 |
# Fine-tuning guide
|
| 323 |
+
https://georgesung.github.io/ai/qlora-ift/
|