Upload model.yml with huggingface_hub

model.yml

@@ -8,7 +8,7 @@ version: 1
 # BEGIN INFERENCE PARAMETERS
 # BEGIN REQUIRED
 stop:
-- <|end_of_text|>
+- <|im_end|>
 # END REQUIRED
 
 # BEGIN OPTIONAL
@@ -40,7 +40,12 @@ min_keep: 0
 # BEGIN MODEL LOAD PARAMETERS
 # BEGIN REQUIRED
 engine: llama-cpp
-prompt_template: <|system|>\n{system_message}\n<|user|>\n{prompt}\n<|assistant|>\n
+prompt_template: |
+  <|im_start|>system
+  {system_message}<|im_end|>
+  <|im_start|>user
+  {prompt}<|im_end|>
+  <|im_start|>assistant
 ctx_len: 4096
 ngl: 34
 # END REQUIRED