log

custom_generate/generate.py

@@ -45,6 +45,7 @@ def generate(model, input_ids, generation_config=None, n_sigma:float=1.0, **kwar
     generation_config = generation_config or model.generation_config  # default to the model generation config
     cur_length = input_ids.shape[1]
     max_length = generation_config.max_length or cur_length + generation_config.max_new_tokens
+    print(f"Starting generation with max_length: {max_length}, current length: {cur_length}")
 
     while cur_length < max_length:
         logits = model(input_ids).logits