diff --git a/README.md b/README.md index 372c0a6..6d0bce2 100644 --- a/README.md +++ b/README.md @@ -1,24 +1,24 @@
-
[ Homepage] | [🤖 Chat with DeepSeek Coder] | [🤗 Models Download] | [Discord] | [Wechat(微信)]
+[ Homepage] | [🤖 Chat with DeepSeek Coder] | [🤗 Models Download] | [Discord] | [Wechat(微信)]
- **Massive Training Data**: Trained on 2T tokens, including 87% code and 13% linguistic data in both English and Chinese languages. - + - **Highly Flexible & Scalable**: Offered in model sizes of 1B, 5.7B, 6.7B and 33B, enabling users to choose the setup most suitable for their requirements. - + - **Superior Model Performance**: State-of-the-art performance among publicly available code models on HumanEval, MultiPL-E, MBPP, DS-1000, and APPS benchmarks. - + - **Advanced Code Completion Capabilities**: A window size of 16K and a fill-in-the-blank task, supporting project-level code completion and infilling tasks. @@ -187,7 +187,7 @@ def load_data(): X_test = torch.tensor(X_test, dtype=torch.float32) y_train = torch.tensor(y_train, dtype=torch.int64) y_test = torch.tensor(y_test, dtype=torch.int64) - + return X_train, X_test, y_train, y_test def evaluate_predictions(y_test, y_pred): @@ -213,7 +213,7 @@ class IrisClassifier(nn.Module): def train_model(self, X_train, y_train, epochs, lr, batch_size): criterion = nn.CrossEntropyLoss() optimizer = optim.Adam(self.parameters(), lr=lr) - + # Create DataLoader for batches dataset = TensorDataset(X_train, y_train) dataloader = DataLoader(dataset, batch_size=batch_size, shuffle=True) @@ -272,4 +272,3 @@ See the [LICENSE-CODE](LICENSE-CODE) and [LICENSE-MODEL](LICENSE-MODEL) for more ### 6. Contact If you have any questions, please raise an issue or contact us at [agi_code@deepseek.com](mailto:agi_code@deepseek.com). -