Instructions to use Maxlegrec/ChessBot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Maxlegrec/ChessBot with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Maxlegrec/ChessBot", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Maxlegrec/ChessBot", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update model architecture: d_ff=1024, new weights from merged7.pt
Browse files- modeling_chessbot.py +1 -1
modeling_chessbot.py
CHANGED
|
@@ -626,7 +626,7 @@ class ChessBotModel(ChessBotPreTrainedModel):
|
|
| 626 |
probs = F.softmax(logits/T, dim=-1)
|
| 627 |
sampled = torch.multinomial(probs, num_samples=1)
|
| 628 |
if return_probs:
|
| 629 |
-
return
|
| 630 |
|
| 631 |
move = policy_index[sampled.item()]
|
| 632 |
return move
|
|
|
|
| 626 |
probs = F.softmax(logits/T, dim=-1)
|
| 627 |
sampled = torch.multinomial(probs, num_samples=1)
|
| 628 |
if return_probs:
|
| 629 |
+
return probs
|
| 630 |
|
| 631 |
move = policy_index[sampled.item()]
|
| 632 |
return move
|