Update README.md
Browse files
README.md
CHANGED
@@ -25,7 +25,7 @@ The primary goal of this model is to improve scores on the ko-CommonGen V2 task,
|
|
25 |
- **Hidden Size**: 2,048
|
26 |
- **FFN Size**: 5,632
|
27 |
- **Maximum Length**: 4,096 tokens
|
28 |
-
- **Training Time**:
|
29 |
|
30 |
#### Limitations and Ethical Considerations
|
31 |
Like other LLMs, the 42dot LLM-SFT-1.3B may produce hallucinated or biased content. Users should be aware of these limitations and take appropriate actions.
|
|
|
25 |
- **Hidden Size**: 2,048
|
26 |
- **FFN Size**: 5,632
|
27 |
- **Maximum Length**: 4,096 tokens
|
28 |
+
- **Training Time**: 5 GPU hours on NVIDIA A100 (Google Colab Pro+)
|
29 |
|
30 |
#### Limitations and Ethical Considerations
|
31 |
Like other LLMs, the 42dot LLM-SFT-1.3B may produce hallucinated or biased content. Users should be aware of these limitations and take appropriate actions.
|