Fix test_qwen2.py

README.md

@@ -170,13 +170,9 @@ WARNING: Currently, the canister can only be build on a `mac` !
       },
     )
 
-    ########################################################
     # NOTE: This is the equivalent llama-cli call, when running llama.cpp locally
     ./llama-cli -m /models/Qwen/Qwen2.5-0.5B-Instruct-GGUF/qwen2.5-0.5b-instruct-q8_0.gguf -sp -p "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\ngive me a short introduction to LLMs.<|im_end|>\n<|im_start|>assistant\n"  -fa -ngl 80 -n 512 --prompt-cache prompt.cache --prompt-cache-all
 
-
-    ```
-
     ########################################
     # Tip. Add this to the args vec if you #
     #      want to see how many tokens the #
@@ -186,6 +182,9 @@ WARNING: Currently, the canister can only be build on a `mac` !
     #      ;"--print-token-count"; "1"     #
     ########################################
 
+    ```
+
+
   - Deployed to mainnet at canister: 6uwoh-vaaaa-aaaag-amema-cai
 
       To be able to upload the model, I had to change the [compute allocation](https://internetcomputer.org/docs/current/developer-docs/smart-contracts/maintain/settings#compute-allocation)
@@ -270,4 +269,5 @@ WARNING: Currently, the canister can only be build on a `mac` !
     #      hits the instruction limit      #
     #                                      #
     #      ;"--print-token-count"; "1"     #
-    ########################################
+    ########################################
+    ```

test/test_qwen2.py

@@ -78,7 +78,7 @@ def test__run_update_1(network: str) -> None:
         canister_argument='(record { args = vec {"--prompt-cache"; "my_cache/prompt.cache"; "--prompt-cache-all"; "-sp"; "-n"; "512"; "-p"; "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\nExplain Large Language Models.<|im_end|>\n<|im_start|>assistant\n"} })',
         network=network,
     )
-    expected_response = '(variant { Ok = record { output = ""; conversation = "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>"; error = ""; status_code = 200 : nat16; prompt_remaining = "user\nExplain Large Language Models.<|im_end|>\n<|im_start|>assistant\n"; generated_eog = false;} })'
+    expected_response = '(variant { Ok = record { output = ""; conversation = "<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n<|im_start|>"; error = ""; status_code = 200 : nat16; prompt_remaining = "user\\nExplain Large Language Models.<|im_end|>\\n<|im_start|>assistant\\n"; generated_eog = false;} })'
     assert expected_response == response
 
 def test__run_update_2(network: str) -> None:
@@ -89,7 +89,7 @@ def test__run_update_2(network: str) -> None:
         canister_argument='(record { args = vec {"--prompt-cache"; "my_cache/prompt.cache"; "--prompt-cache-all"; "-sp"; "-n"; "512"; "-p"; "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\nExplain Large Language Models.<|im_end|>\n<|im_start|>assistant\n"} })',
         network=network,
     )
-    expected_response = '(variant { Ok = record { status_code = 200 : nat16; error = ""; output = ""; input = "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\nExplain Large Language Models.<|im_end|>\n<|im_start|>assistant"; prompt_remaining = "\n";} generated_eog=false : bool})'
+    expected_response = '(variant { Ok = record { output = ""; conversation = "<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n<|im_start|>user\\nExplain Large Language Models.<|im_end|>\\n<|im_start|>assistant"; error = ""; status_code = 200 : nat16; prompt_remaining = "\\n"; generated_eog = false;} })'
     assert expected_response == response
 
 def test__run_update_3(network: str) -> None: