Upload LoRA adapter (README written by author)
Browse files- README.md +1 -1
- adapter_model.safetensors +1 -1
README.md
CHANGED
|
@@ -35,7 +35,7 @@ while intermediate reasoning (Chain-of-Thought) is masked.
|
|
| 35 |
- Method: QLoRA (4-bit)
|
| 36 |
- Max sequence length: 512
|
| 37 |
- Epochs: 1
|
| 38 |
-
- Learning rate:
|
| 39 |
- LoRA: r=64, alpha=128
|
| 40 |
|
| 41 |
## Usage
|
|
|
|
| 35 |
- Method: QLoRA (4-bit)
|
| 36 |
- Max sequence length: 512
|
| 37 |
- Epochs: 1
|
| 38 |
+
- Learning rate: 2e-06
|
| 39 |
- LoRA: r=64, alpha=128
|
| 40 |
|
| 41 |
## Usage
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 113255736
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41adc7d470d0d82719c5a2784d428ff4d27ce47f03582892c4b5b49e675df6f6
|
| 3 |
size 113255736
|