Update README.md
Browse files
README.md
CHANGED
|
@@ -10,7 +10,7 @@ We made a LLM model with davidkim205/nox-solar-10.7b-v4
|
|
| 10 |
|
| 11 |
## Model Description
|
| 12 |
We use QLoRA(256, 64) and NEFTune on LLM Fine-tuning
|
| 13 |
-
lr = 1e-5
|
| 14 |
|
| 15 |
## Train Detail
|
| 16 |
Our changed private data used, 5 epoch train, and parameter changed
|
|
|
|
| 10 |
|
| 11 |
## Model Description
|
| 12 |
We use QLoRA(256, 64) and NEFTune on LLM Fine-tuning
|
| 13 |
+
lr = 1e-5, NEFTune = 3
|
| 14 |
|
| 15 |
## Train Detail
|
| 16 |
Our changed private data used, 5 epoch train, and parameter changed
|