Update README.md
Browse files
README.md
CHANGED
|
@@ -51,6 +51,7 @@ $$
|
|
| 51 |
$$
|
| 52 |
|
| 53 |
Where:
|
|
|
|
| 54 |
- $\theta_s$ and $\theta_t$ represent student (trainable) and teacher (frozen) model parameters
|
| 55 |
- $P_{\theta}^{(i)}$ denotes the probability distribution at reasoning step $i$
|
| 56 |
- $\lambda(t) = \lambda_0 \cdot (1 + \gamma \cdot \text{complexity}(x_t))$ is the dynamic weight function
|
|
|
|
| 51 |
$$
|
| 52 |
|
| 53 |
Where:
|
| 54 |
+
|
| 55 |
- $\theta_s$ and $\theta_t$ represent student (trainable) and teacher (frozen) model parameters
|
| 56 |
- $P_{\theta}^{(i)}$ denotes the probability distribution at reasoning step $i$
|
| 57 |
- $\lambda(t) = \lambda_0 \cdot (1 + \gamma \cdot \text{complexity}(x_t))$ is the dynamic weight function
|