fix double bos/eos jinja avoidance hack (was preventing inner bos/eos tokens)

Author: ochafik

common/chat.cpp

@@ -582,10 +582,17 @@ static std::string apply(
     // tmpl_inputs.now = std::chrono::system_clock::now();
 
     minja::chat_template_options tmpl_opts;
-    tmpl_opts.use_bos_token = false;
-    tmpl_opts.use_eos_token = false;
-
-    return tmpl.apply(tmpl_inputs, tmpl_opts);
+    // To avoid double BOS / EOS tokens, we're manually removing begining / trailing tokens
+    // instead of using `chat_template_options.use_bos_token = false`, since these tokens
+    // may be needed inside the template / between messages too.
+    auto result = tmpl.apply(tmpl_inputs, tmpl_opts);
+    if (string_starts_with(result, tmpl.bos_token())) {
+        result = result.substr(tmpl.bos_token().size());
+    }
+    if (string_ends_with(result, tmpl.eos_token())) {
+        result = result.substr(0, result.size() - tmpl.eos_token().size());
+    }
+    return result;
 }
 
 static common_chat_params common_chat_params_init_generic(const common_chat_template & tmpl, const struct templates_params & inputs) {

tests/test-chat-template.cpp

@@ -57,7 +57,7 @@ int main(void) {
             /* .template_str= */ "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
             /* .expected_output= */ "[INST] You are a helpful assistant\nHello [/INST]Hi there</s>[INST] Who are you [/INST]   I am an assistant   </s>[INST] Another question [/INST]",
             /* .expected_output_jinja= */ "",
-            /* .bos_token= */ "",
+            /* .bos_token= */ "<s>",
             /* .eos_token= */ "</s>",
         },
         {
@@ -79,8 +79,8 @@ int main(void) {
         {
             /* .name= */ "mlabonne/AlphaMonarch-7B",
             /* .template_str= */ "{% for message in messages %}{{bos_token + message['role'] + '\\n' + message['content'] + eos_token + '\\n'}}{% endfor %}{% if add_generation_prompt %}{{ bos_token + 'assistant\\n' }}{% endif %}",
-            /* .expected_output= */          "system\nYou are a helpful assistant</s>\n<s>user\nHello</s>\n<s>assistant\nHi there</s>\n<s>user\nWho are you</s>\n<s>assistant\n   I am an assistant   </s>\n<s>user\nAnother question</s>\n<s>assistant\n",
-            /* .expected_output_jinja= */ "<s>system\nYou are a helpful assistant</s>\n<s>user\nHello</s>\n<s>assistant\nHi there</s>\n<s>user\nWho are you</s>\n<s>assistant\n   I am an assistant   </s>\n<s>user\nAnother question</s>\n<s>assistant\n",
+            /* .expected_output= */       "system\nYou are a helpful assistant</s>\n<s>user\nHello</s>\n<s>assistant\nHi there</s>\n<s>user\nWho are you</s>\n<s>assistant\n   I am an assistant   </s>\n<s>user\nAnother question</s>\n<s>assistant\n",
+            /* .expected_output_jinja= */ "system\nYou are a helpful assistant</s>\n<s>user\nHello</s>\n<s>assistant\nHi there</s>\n<s>user\nWho are you</s>\n<s>assistant\n   I am an assistant   </s>\n<s>user\nAnother question</s>\n<s>assistant\n",
             /* .bos_token= */ "<s>",
             /* .eos_token= */ "</s>",
         },
@@ -94,7 +94,7 @@ int main(void) {
             /* .name= */ "OrionStarAI/Orion-14B-Chat",
             /* .template_str= */ "{% for message in messages %}{% if loop.first %}{{ bos_token }}{% endif %}{% if message['role'] == 'user' %}{{ 'Human: ' + message['content'] + '\\n\\nAssistant: ' + eos_token }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token }}{% endif %}{% endfor %}",
             /* .expected_output= */       "Human: You are a helpful assistant\n\nHello\n\nAssistant: </s>Hi there</s>Human: Who are you\n\nAssistant: </s>   I am an assistant   </s>Human: Another question\n\nAssistant: </s>",
-            /* .expected_output_jinja= */ "Human: You are a helpful assistant\nHello\n\nAssistant: </s>Hi there</s>Human: Who are you\n\nAssistant: </s>   I am an assistant   </s>Human: Another question\n\nAssistant: </s>",
+            /* .expected_output_jinja= */ "Human: You are a helpful assistant\nHello\n\nAssistant: </s>Hi there</s>Human: Who are you\n\nAssistant: </s>   I am an assistant   </s>Human: Another question\n\nAssistant: ",
             /* .bos_token= */ "",
             /* .eos_token= */ "</s>",
         },
@@ -323,7 +323,7 @@ int main(void) {
         try {
             common_chat_templates_ptr tmpls(common_chat_templates_init(/* model= */ nullptr, test_case.template_str.c_str(), test_case.bos_token, test_case.eos_token), &common_chat_templates_free);
             common_chat_templates_inputs inputs;
-            inputs.use_jinja = false;
+            inputs.use_jinja = true;
             inputs.messages = messages;
             inputs.add_generation_prompt = add_generation_prompt;
             auto output = common_chat_templates_apply(tmpls.get(), inputs).prompt;