Update README.md

README.md

@@ -43,7 +43,7 @@ The model outputs two vectors:
 1.  **Policy**: A probability distribution over `NUM_POSSIBLE_MOVES=4672` representing the probability of making each move, obtained using `softmax` activation.
 2.  **Value**: A single scalar value indicating win/loss probability from current player’s perspective, ranging from -1 (loss) to 1 (win), obtained using `tanh` activation.
 
-[![StockZero Demo Gameplay Video](https://huggingface.co/nirajandhakal/StockZero/blob/main/demo_video_thumbnail.png)](https://huggingface.co/nirajandhakal/StockZero/blob/main/v2-gameplay-svg-high-quality.mp4)
+
 
 ### Model Architecture
 
@@ -128,6 +128,12 @@ This model was evaluated against a simple random move opponent using the `evalua
 
 These scores indicate that the model, in its current state, is not a strong chess player. It draws a majority of games against a random opponent, but also loses a significant number. Further training and architecture improvements are needed to enhance its performance.
 
+
+## Demo Game Video
+
+You can see a demo game here: [StockZero Demo Gameplay Video](https://huggingface.co/nirajandhakal/StockZero/blob/main/v2-gameplay-svg-high-quality.mp4)
+
+
 ## How to Use
 
 ### Training