Fix partial unicode characters issue (#4837)

modules/exllamav2.py

@@ -138,11 +138,19 @@ class Exllamav2Model:
             if has_leading_space:
                 decoded_text = ' ' + decoded_text
 
-            yield decoded_text
+            # Check the partial unicode character
+            if chr(0xfffd) in decoded_text:
+                is_last = i == max_new_tokens - 1
+                is_stopping = token.item() == self.tokenizer.eos_token_id or shared.stop_everything
+                # If we are not at the end of the generation, we skip this token
+                if not (is_last or is_stopping):
+                    continue
 
             if token.item() == self.tokenizer.eos_token_id or shared.stop_everything:
                 break
 
+            yield decoded_text
+
     def generate(self, prompt, state):
         output = ''
         for output in self.generate_with_streaming(prompt, state):