abetlen · abetlen · Apr 18, 2023 · Apr 10, 2023 · Apr 17, 2023 · Apr 17, 2023
diff --git a/examples/low_level_api/common.py b/examples/low_level_api/common.py
@@ -50,7 +50,7 @@ class GptParams:
     # If chat ended prematurely, append this to the conversation to fix it.
     # Set to "\nUser:" etc.
     # This is an alternative to input_prefix which always adds it, so it potentially duplicates "User:""
-    fix_prefix: str = " "
+    fix_prefix: str = ""
     output_postfix: str = ""
     input_echo: bool = True,
 
@@ -75,7 +75,7 @@ def gpt_params_parse(argv = None, params: Optional[GptParams] = None):
     parser.add_argument("--top_p", type=float, default=0.95, help="top-p samplin",dest="top_p")
     parser.add_argument("--top_k", type=int, default=40, help="top-k sampling",dest="top_k")
     parser.add_argument("--temp", type=float, default=0.80, help="temperature",dest="temp")
-    parser.add_argument("--n_predict", type=int, default=128, help="number of model parts",dest="n_predict")
+    parser.add_argument("--n_predict", type=int, default=128, help="number of tokens to predict (-1 = infinity)",dest="n_predict")
     parser.add_argument("--repeat_last_n", type=int, default=64, help="last n tokens to consider for penalize ",dest="repeat_last_n")
     parser.add_argument("--repeat_penalty", type=float, default=1.10, help="penalize repeat sequence of tokens",dest="repeat_penalty")
     parser.add_argument("-b", "--batch_size", type=int, default=8, help="batch size for prompt processing",dest="n_batch")

diff --git a/examples/low_level_api/low_level_api_chat_cpp.py b/examples/low_level_api/low_level_api_chat_cpp.py
@@ -144,6 +144,7 @@ def __init__(self, params: GptParams) -> None:
 
 		# determine newline token
 		self.llama_token_newline = self._tokenize("\n", False)
+		self.llama_token_eot = self._tokenize(" [end of text]\n", False)
 
 		if (self.params.verbose_prompt):
 			print(f"""
@@ -203,16 +204,16 @@ def _tokenize(self, prompt, bos=True):
 		_n = llama_cpp.llama_tokenize(self.ctx, prompt.encode("utf8"), _arr, len(_arr), bos)
 		return _arr[:_n]
 
-	def use_antiprompt(self):
-		return len(self.first_antiprompt) > 0
-
 	def set_color(self, c):
 		if (self.params.use_color):
 			print(c, end="")
 
+	def use_antiprompt(self):
+		return len(self.first_antiprompt) > 0
+
 	# generate tokens
 	def generate(self):
-		while self.remaining_tokens > 0 or self.params.interactive:
+		while self.remaining_tokens > 0 or self.params.interactive or self.params.n_predict == -1:
 			# predict
 			if len(self.embd) > 0:
 				# infinite text generation via context swapping
@@ -313,7 +314,7 @@ def generate(self):
 			# end of text token
 			if len(self.embd) > 0 and self.embd[-1] == llama_cpp.llama_token_eos():
 				if (not self.params.instruct):
-					for i in " [end of text]\n":
+					for i in self.llama_token_eot:
 						yield i
 				break