mirror of
https://github.com/karpathy/nanochat.git
synced 2026-05-08 16:59:59 +00:00
Training data taught the model to echo another <|output_start|>…<|output_end|> after our injected real tool result. Detect that second sequence and break the turn; the grounded answer has already streamed to the client. |
||
|---|---|---|
| .. | ||
| _model.py | ||
| _tokenizer.py | ||
| _tools.py | ||
| serve.py | ||