fix

ztxz16 · Jun 24, 2024 · 89b2658 · 89b2658
1 parent 5ae5cea
commit 89b2658
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/example/openai_server/fastllm_completion.py b/example/openai_server/fastllm_completion.py
@@ -55,7 +55,7 @@ def init_fast_llm_model(self):
     llm.set_cpu_threads(self.cpu_thds)
     llm.set_cpu_low_mem(self.low_mem_mode)
     llm.set_cuda_embedding(self.cuda_embedding)
-    self.model = llm.model(self.model_path, dtype = self.dtype, tokenizer_type = "fastllm")
+    self.model = llm.model(self.model_path, dtype = self.dtype, tokenizer_type = "auto")
     self.model.set_atype(self.atype)
 
   def create_error_response(