Update README.md
Browse files
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
-
# Simple
|
2 |
|
3 |
-
Simple
|
4 |
|
5 |
## Acknowledgements
|
6 |
|
@@ -11,7 +11,7 @@ Simple LLaMa FineTuner is a user-friendly interface designed to facilitate fine-
|
|
11 |
|
12 |
## Features
|
13 |
|
14 |
-
- Fine-tuning
|
15 |
- Simply paste datasets in the UI, separated by double blank lines
|
16 |
- Adjustable parameters for fine-tuning and inference
|
17 |
- Begner-friendly UI with explanations for each parameter
|
|
|
1 |
+
# Simple LLaMA FineTuner
|
2 |
|
3 |
+
Simple LLaMA FineTuner is a user-friendly interface designed to facilitate fine-tuning the LLaMA-7B language model using peft/LoRA method. With this intuitive UI, you can easily manage your dataset, customize parameters, train, and evaluate the model's inference capabilities.
|
4 |
|
5 |
## Acknowledgements
|
6 |
|
|
|
11 |
|
12 |
## Features
|
13 |
|
14 |
+
- Fine-tuning LLaMA-7B on NVIDIA GTX 3090 (or similar hardware)
|
15 |
- Simply paste datasets in the UI, separated by double blank lines
|
16 |
- Adjustable parameters for fine-tuning and inference
|
17 |
- Begner-friendly UI with explanations for each parameter
|