samfundev
diff --git a/‎examples/low_level_api/low_level_api_chat_cpp.py
Copy file name to clipboardExpand all lines: examples/low_level_api/low_level_api_chat_cpp.py
+11-8Lines changed: 11 additions & 8 deletions b/‎examples/low_level_api/low_level_api_chat_cpp.py
Copy file name to clipboardExpand all lines: examples/low_level_api/low_level_api_chat_cpp.py
+11-8Lines changed: 11 additions & 8 deletions
diff --git a/‎pyproject.toml
Copy file name to clipboardExpand all lines: pyproject.toml
+1-1Lines changed: 1 addition & 1 deletion b/‎pyproject.toml
Copy file name to clipboardExpand all lines: pyproject.toml
+1-1Lines changed: 1 addition & 1 deletion
diff --git a/‎setup.py
Copy file name to clipboardExpand all lines: setup.py
+1-1Lines changed: 1 addition & 1 deletion b/‎setup.py
Copy file name to clipboardExpand all lines: setup.py
+1-1Lines changed: 1 addition & 1 deletion
@@ -368,10 +368,10 @@ def generate(self):
 						id = llama_cpp.llama_sample_token_mirostat_v2(self.ctx, candidates_p, llama_cpp.c_float(self.params.mirostat_tau), llama_cpp.c_float(self.params.mirostat_eta), llama_cpp.c_float(mirostat_mu))
 					else:
 						# Temperature sampling
-						llama_cpp.llama_sample_top_k(self.ctx, candidates_p, top_k)
-						llama_cpp.llama_sample_tail_free(self.ctx, candidates_p, llama_cpp.c_float(self.params.tfs_z))
-						llama_cpp.llama_sample_typical(self.ctx, candidates_p, llama_cpp.c_float(self.params.typical_p))
-						llama_cpp.llama_sample_top_p(self.ctx, candidates_p, llama_cpp.c_float(self.params.top_p))
+						llama_cpp.llama_sample_top_k(self.ctx, candidates_p, top_k, min_keep=llama_cpp.c_size_t(1))
+						llama_cpp.llama_sample_tail_free(self.ctx, candidates_p, llama_cpp.c_float(self.params.tfs_z), min_keep=llama_cpp.c_size_t(1))
+						llama_cpp.llama_sample_typical(self.ctx, candidates_p, llama_cpp.c_float(self.params.typical_p), min_keep=llama_cpp.c_size_t(1))
+						llama_cpp.llama_sample_top_p(self.ctx, candidates_p, llama_cpp.c_float(self.params.top_p), min_keep=llama_cpp.c_size_t(1))
 						llama_cpp.llama_sample_temperature(self.ctx, candidates_p, llama_cpp.c_float(self.params.temp))
 						id = llama_cpp.llama_sample_token(self.ctx, candidates_p)
 				# print("`{}`".format(candidates_p.size))
@@ -382,12 +382,15 @@ def generate(self):
 				# replace end of text token with newline token when in interactive mode
 				if (id == llama_cpp.llama_token_eos() and self.params.interactive and not self.params.instruct):
 					id = self.llama_token_newline[0]
+					self.embd.append(id)
 					if (self.use_antiprompt()):
 						# tokenize and inject first reverse prompt
 						self.embd_inp += self.first_antiprompt[0]
-
-				# add it to the context
-				self.embd.append(id)
+						for id in self.first_antiprompt[0]:
+							self.embd.append(id)
+				else:
+					# add it to the context
+					self.embd.append(id)
 
 				# echo this to console
 				self.output_echo = True
@@ -493,7 +496,7 @@ def output(self):
 			# Contains multi-byte UTF8
 			for num, pattern in [(2, 192), (3, 224), (4, 240)]:
 				# Bitwise AND check
-				if pattern & int.from_bytes(cur_char) == pattern:
+				if pattern & int.from_bytes(cur_char, 'little') == pattern:
 					self.multibyte_fix = [cur_char] + ([None] * (num-1))
 
 			# Stop incomplete bytes from passing
 
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "llama_cpp_python"
-version = "0.1.54"
+version = "0.1.55"
 description = "Python bindings for the llama.cpp library"
 authors = ["Andrei Betlen <abetlen@gmail.com>"]
 license = "MIT"
 
@@ -10,7 +10,7 @@
     description="A Python wrapper for llama.cpp",
     long_description=long_description,
     long_description_content_type="text/markdown",
-    version="0.1.54",
+    version="0.1.55",
     author="Andrei Betlen",
     author_email="abetlen@gmail.com",
     license="MIT",