Update README.md

README.md

@@ -12,7 +12,6 @@ base_model:
 ## Model Overview
 
 DMind-2 is a series of Web3 investment analysis language models specifically designed for edge deployment, dedicated to providing real-time, private, and professional Web3 investment consulting services for individual investors and professional institutions. Standing on the shoulders of numerous open-source pioneers, we have successfully launched three model variants through innovative post-training techniques, enabling users to access institutional-grade investment analysis capabilities on local devices without concerns about data privacy or network latency.
-
 ## Core Positioning
 
 DMind-2 focuses on **edge-side Web3 investment opinion generation, financial consulting services, and comprehensive financial investment computational analysis**, representing the industry's first professional-grade Web3 investment analysis model truly optimized for edge deployment. Through careful model compression and optimization, DMind2-mini runs smoothly with just 4GB of VRAM, allowing every investor to have their own dedicated investment advisor on personal devices.
@@ -51,12 +50,14 @@ DMind-2's greatest technical breakthrough lies in our innovative Distribution-Pr
 
 The DPCD optimization objective combines domain adaptation with reasoning preservation through the following loss function:
 
-$\mathcal{L}_{\text{DPCD}} = \underbrace{\mathcal{L}_{\text{CE}}(\theta_s, \mathcal{D}_{\text{Web3}})}_{\text{Domain Learning}} + \underbrace{\lambda(t) \cdot \sum_{i=1}^{T} \alpha_i \cdot D_{\text{KL}}(P_{\theta_s}^{(i)} \| P_{\theta_t}^{(i)})}_{\text{Distribution Preservation}} + \underbrace{\beta \cdot \mathcal{L}_{\text{QS}}(\mathcal{C}_{\theta_s})}_{\text{Quality Score}}$
+$$
+\mathcal{L}_{\text{DPCD}} = \underbrace{\mathcal{L}_{\text{CE}}(\theta_s, \mathcal{D}_{\text{Web3}})}_{\text{Domain Learning}} + \underbrace{\lambda(t) \cdot \sum_{i=1}^{T} \alpha_i \cdot D_{\text{KL}}(P_{\theta_s}^{(i)} \| P_{\theta_t}^{(i)})}_{\text{Distribution Preservation}} + \underbrace{\beta \cdot \mathcal{L}_{\text{QS}}(\mathcal{C}_{\theta_s})}_{\text{Quality Score}}
+$$
 
 Where:
-- $\theta_s$ and $\theta_t$ represent student (trainable) and teacher (frozen) model parameters
-- $P_{\theta}^{(i)}$ denotes the probability distribution at reasoning step $i$
-- $\lambda(t) = \lambda_0 \cdot (1 + \gamma \cdot \text{complexity}(x_t))$ is the dynamic weight function
+- $ \theta_s $ and $ \theta_t $ represent student (trainable) and teacher (frozen) model parameters
+- $$P_{\theta}^{(i)}$$ denotes the probability distribution at reasoning step $$i$$
+- $$ \lambda(t) = \lambda_0 \cdot (1 + \gamma \cdot \text{complexity}(x_t)) $$ is the dynamic weight function
 - $\alpha_i = \exp(-\delta \cdot i/T)$ implements exponential decay for later reasoning steps
 - $\mathcal{L}_{\text{QS}}$ is the quality scoring loss ensuring reasoning coherence