Upload moondream.py

moondream.py

@@ -86,7 +86,14 @@ class Moondream(PreTrainedModel):
                 inputs_embeds=inputs_embeds, streamer=streamer, **generate_config
             )
 
-        return tokenizer.batch_decode(output_ids, skip_special_tokens=True)
+            # Pull the generated text from the streamer, and update the model output.
+            model_output = ""
+            for new_text in streamer:
+                model_output += new_text
+                yield new_text
+            return model_output
+
+        #return tokenizer.batch_decode(output_ids, skip_special_tokens=True)