Instructions to use gae-m/codesage-base-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use gae-m/codesage-base-v2 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import CodeSage model = CodeSage.from_pretrained("gae-m/codesage-base-v2", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload modeling_codesage.py with huggingface_hub
Browse files- modeling_codesage.py +1 -0
modeling_codesage.py
CHANGED
|
@@ -185,6 +185,7 @@ class CodeSageModel(CodeSagePreTrainedModel):
|
|
| 185 |
self.ln_f = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_epsilon)
|
| 186 |
|
| 187 |
self.init_weights()
|
|
|
|
| 188 |
|
| 189 |
def get_input_embeddings(self):
|
| 190 |
return self.wte
|
|
|
|
| 185 |
self.ln_f = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_epsilon)
|
| 186 |
|
| 187 |
self.init_weights()
|
| 188 |
+
self.post_init()
|
| 189 |
|
| 190 |
def get_input_embeddings(self):
|
| 191 |
return self.wte
|