tool-call: allow --chat-template chatml w/ --jinja, default to chatml upon parsing issue, avoid double bos (ggml-org#11616)

* tool-call: allow `--jinja --chat-template chatml`

* fix double bos issue (drop bos/eos tokens from jinja template)

* add missing try catch around jinja parsing to default to chatml

* Simplify default chatml logic

Author: ochafik

common/common.cpp

@@ -1869,11 +1869,19 @@ std::string common_chat_format_example(const common_chat_template & tmpl, bool u
     return common_chat_apply_template(tmpl, msgs, true, use_jinja);
 }
 
+#define CHATML_TEMPLATE_SRC \
+    "{%- for message in messages -%}\n" \
+    "  {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' -}}\n" \
+    "{%- endfor -%}\n" \
+    "{%- if add_generation_prompt -%}\n" \
+    "  {{- '<|im_start|>assistant\n' -}}\n" \
+    "{%- endif -%}"
+
 common_chat_templates common_chat_templates_from_model(const struct llama_model * model, const std::string & chat_template_override)
 {
-    auto vocab = llama_model_get_vocab(model);
-    std::string default_template_src = chat_template_override;
-    std::string template_tool_use_src = chat_template_override;
+    std::string default_template_src;
+    std::string template_tool_use_src;
+
     bool has_explicit_template = !chat_template_override.empty();
     if (chat_template_override.empty()) {
         auto str = llama_model_chat_template(model, /* name */ nullptr);
@@ -1886,21 +1894,21 @@ common_chat_templates common_chat_templates_from_model(const struct llama_model
             template_tool_use_src = str;
             has_explicit_template = true;
         }
+    } else {
+        default_template_src = chat_template_override;
     }
     if (default_template_src.empty() || default_template_src == "chatml") {
         if (!template_tool_use_src.empty()) {
             default_template_src = template_tool_use_src;
         } else {
-            default_template_src = R"(
-                {%- for message in messages -%}
-                    {{- "<|im_start|>" + message.role + "\n" + message.content + "<|im_end|>\n" -}}
-                {%- endfor -%}
-                {%- if add_generation_prompt -%}
-                    {{- "<|im_start|>assistant\n" -}}
-                {%- endif -%}
-            )";
+            default_template_src = CHATML_TEMPLATE_SRC;
         }
     }
+    std::string token_bos;
+    std::string token_eos;
+    // TODO: update logic that adds BOS and EOS tokens to the tokenized prompt, in favour of the template.
+#if 0
+    auto vocab = llama_model_get_vocab(model);
     const auto get_token = [&](llama_token token, const char * name, const char * jinja_variable_name) {
         if (token == LLAMA_TOKEN_NULL) {
             if (default_template_src.find(jinja_variable_name) != std::string::npos
@@ -1912,15 +1920,25 @@ common_chat_templates common_chat_templates_from_model(const struct llama_model
             return common_token_to_piece(vocab, token, true);
         }
     };
-    auto token_bos = get_token(llama_vocab_bos(vocab), "BOS", "bos_token");
-    auto token_eos = get_token(llama_vocab_eos(vocab), "EOS", "eos_token");
-    return {
-        has_explicit_template,
-        std::make_unique<minja::chat_template>(default_template_src, token_bos, token_eos),
-        template_tool_use_src.empty()
-            ? nullptr
-            : std::make_unique<minja::chat_template>(template_tool_use_src, token_bos, token_eos)
-    };
+    token_bos = get_token(llama_vocab_bos(vocab), "BOS", "bos_token");
+    token_eos = get_token(llama_vocab_eos(vocab), "EOS", "eos_token");
+#endif
+    try {
+        return {
+            has_explicit_template,
+            std::make_unique<minja::chat_template>(default_template_src, token_bos, token_eos),
+            template_tool_use_src.empty()
+                ? nullptr
+                : std::make_unique<minja::chat_template>(template_tool_use_src, token_bos, token_eos),
+        };
+    } catch (const std::exception & e) {
+        LOG_ERR("%s: failed to parse chat template: %s\n", __func__, e.what());
+        return {
+            has_explicit_template,
+            std::make_unique<minja::chat_template>(CHATML_TEMPLATE_SRC, token_bos, token_eos),
+            nullptr,
+        };
+    }
 }
 
 //

examples/server/tests/unit/test_chat_completion.py

@@ -13,9 +13,12 @@ def create_server():
 @pytest.mark.parametrize(
     "model,system_prompt,user_prompt,max_tokens,re_content,n_prompt,n_predicted,finish_reason,jinja,chat_template",
     [
+        (None, "Book", "Hey", 8, "But she couldn't", 69, 8, "length", False, None),
+        (None, "Book", "Hey", 8, "But she couldn't", 69, 8, "length", True, None),
         (None, "Book", "What is the best book", 8, "(Suddenly)+|\\{ \" Sarax.", 77, 8, "length", False, None),
-        (None, "Book", "What is the best book", 8, "(Suddenly)+|\\{ \" Sarax.", 77, 8, "length", True, None),
-        (None, "Book", "What is the best book", 8, "^ blue", 23, 8, "length", True, "This is not a chat template, it is"),
+        (None, "Book", "What is the best book", 8, "(Suddenly)+|\\{ \" Sarax.", 77, 8, "length", True,  None),
+        (None, "Book", "What is the best book", 8, "(Suddenly)+|\\{ \" Sarax.", 77, 8, "length", True, 'chatml'),
+        (None, "Book", "What is the best book", 8, "^ blue",                    23, 8, "length", True, "This is not a chat template, it is"),
         ("codellama70b", "You are a coding assistant.", "Write the fibonacci function in c++.", 128, "(Aside|she|felter|alonger)+", 104, 64, "length", False, None),
         ("codellama70b", "You are a coding assistant.", "Write the fibonacci function in c++.", 128, "(Aside|she|felter|alonger)+", 104, 64, "length", True, None),
     ]

examples/server/tests/unit/test_tool_call.py

@@ -67,8 +67,8 @@ def create_server():
 
 
 def do_test_completion_with_required_tool_tiny(template_name: str, tool: dict, argument_key: str | None):
-    n_predict = 512
     global server
+    n_predict = 512
     # server = ServerPreset.stories15m_moe()
     server.jinja = True
     server.n_predict = n_predict
@@ -139,40 +139,62 @@ def test_completion_with_required_tool_tiny_slow(template_name: str, tool: dict,
 @pytest.mark.parametrize("tool,argument_key,hf_repo,template_override", [
     (TEST_TOOL,    "success",  "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", None),
     (PYTHON_TOOL,  "code",     "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", None),
+    (PYTHON_TOOL,  "code",     "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", "chatml"),
+
+    # Note: gemma-2-2b-it knows itself as "model", not "assistant", so we don't test the ill-suited chatml on it.
     (TEST_TOOL,    "success",  "bartowski/gemma-2-2b-it-GGUF:Q4_K_M",              None),
     (PYTHON_TOOL,  "code",     "bartowski/gemma-2-2b-it-GGUF:Q4_K_M",              None),
+
     (TEST_TOOL,    "success",  "bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M",      None),
     (PYTHON_TOOL,  "code",     "bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M",      None),
+    (PYTHON_TOOL,  "code",     "bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M",      "chatml"),
+
     (TEST_TOOL,    "success",  "bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M",        None),
     (PYTHON_TOOL,  "code",     "bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M",        None),
+    (PYTHON_TOOL,  "code",     "bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M",        "chatml"),
+
     (TEST_TOOL,    "success",  "bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-2-Pro-Llama-3-8B", "tool_use")),
     (PYTHON_TOOL,  "code",     "bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-2-Pro-Llama-3-8B", "tool_use")),
+    (PYTHON_TOOL,  "code",     "bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", "chatml"),
+
     (TEST_TOOL,    "success",  "bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M",   ("NousResearch/Hermes-3-Llama-3.1-8B", "tool_use")),
     (PYTHON_TOOL,  "code",     "bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M",   ("NousResearch/Hermes-3-Llama-3.1-8B", "tool_use")),
+    (PYTHON_TOOL,  "code",     "bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M",   "chatml"),
+
     (TEST_TOOL,    "success",  "bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", None),
     (PYTHON_TOOL,  "code",     "bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", None),
-    (TEST_TOOL,    "success",  "bartowski/functionary-small-v3.2-GGUF:Q8_0",       ("meetkai/functionary-medium-v3.2", None)),
-    (PYTHON_TOOL,  "code",     "bartowski/functionary-small-v3.2-GGUF:Q8_0",       ("meetkai/functionary-medium-v3.2", None)),
+    (PYTHON_TOOL,  "code",     "bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", "chatml"),
+
+    (TEST_TOOL,    "success",  "bartowski/functionary-small-v3.2-GGUF:Q4_K_M",       ("meetkai/functionary-medium-v3.2", None)),
+    (PYTHON_TOOL,  "code",     "bartowski/functionary-small-v3.2-GGUF:Q4_K_M",       ("meetkai/functionary-medium-v3.2", None)),
+    (PYTHON_TOOL,  "code",     "bartowski/functionary-small-v3.2-GGUF:Q4_K_M",       "chatml"),
+
     (TEST_TOOL,    "success",  "bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M",      ("meta-llama/Llama-3.2-3B-Instruct", None)),
     (PYTHON_TOOL,  "code",     "bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M",      ("meta-llama/Llama-3.2-3B-Instruct", None)),
+    (PYTHON_TOOL,  "code",     "bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M",      "chatml"),
+
     (TEST_TOOL,    "success",  "bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M",      ("meta-llama/Llama-3.2-3B-Instruct", None)),
     (PYTHON_TOOL,  "code",     "bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M",      ("meta-llama/Llama-3.2-3B-Instruct", None)),
+    (PYTHON_TOOL,  "code",     "bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M",      "chatml"),
     # TODO: fix these
     # (TEST_TOOL,    "success",  "bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M", None),
     # (PYTHON_TOOL,  "code",     "bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M", None),
 ])
-def test_completion_with_required_tool_real_model(tool: dict, argument_key: str | None, hf_repo: str, template_override: Tuple[str, str | None] | None):
+def test_completion_with_required_tool_real_model(tool: dict, argument_key: str | None, hf_repo: str, template_override: str | Tuple[str, str | None] | None):
+    global server
     n_predict = 512
     server.n_slots = 1
     server.jinja = True
     server.n_ctx = 8192
     server.n_predict = n_predict
     server.model_hf_repo = hf_repo
     server.model_hf_file = None
-    if template_override:
+    if isinstance(template_override, tuple):
         (template_hf_repo, template_variant) = template_override
         server.chat_template_file = f"../../../models/templates/{template_hf_repo.replace('/', '-') + ('-' + template_variant if template_variant else '')}.jinja"
         assert os.path.exists(server.chat_template_file), f"Template file {server.chat_template_file} does not exist. Run `python scripts/get_chat_template.py {template_hf_repo} {template_variant} > {server.chat_template_file}` to download the template."
+    elif isinstance(template_override, str):
+        server.chat_template = template_override
     server.start(timeout_seconds=TIMEOUT_SERVER_START)
     res = server.make_request("POST", "/chat/completions", data={
         "max_tokens": n_predict,
@@ -252,29 +274,49 @@ def test_completion_without_tool_call_slow(template_name: str, n_predict: int, t
 @pytest.mark.slow
 @pytest.mark.parametrize("hf_repo,template_override", [
     ("bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", None),
-    ("bartowski/gemma-2-2b-it-GGUF:Q4_K_M",              None),
+    ("bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", "chatml"),
+
     ("bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M",      None),
+    ("bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M",      "chatml"),
+
     ("bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M",        None),
-    ("bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-2-Pro-Llama-3-8B", "tool_use")),
-    ("bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M",   ("NousResearch/Hermes-3-Llama-3.1-8B", "tool_use")),
+    ("bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M",        "chatml"),
+
+    ("bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M",    ("NousResearch/Hermes-2-Pro-Llama-3-8B", "tool_use")),
+    ("bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M",    "chatml"),
+
+    ("bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M",      ("NousResearch/Hermes-3-Llama-3.1-8B", "tool_use")),
+    ("bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M",      "chatml"),
+
     ("bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", None),
+    ("bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", "chatml"),
+
     ("bartowski/functionary-small-v3.2-GGUF:Q8_0",       ("meetkai/functionary-medium-v3.2", None)),
+    ("bartowski/functionary-small-v3.2-GGUF:Q8_0",       "chatml"),
+
     ("bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M",      ("meta-llama/Llama-3.2-3B-Instruct", None)),
+    ("bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M",      "chatml"),
+
+    # Note: gemma-2-2b-it knows itself as "model", not "assistant", so we don't test the ill-suited chatml on it.
+    ("bartowski/gemma-2-2b-it-GGUF:Q4_K_M",              None),
+
     # ("bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M", ("meta-llama/Llama-3.2-3B-Instruct", None)),
     # ("bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M", None),
 ])
-def test_weather_tool_call(hf_repo: str, template_override: Tuple[str, str | None] | None):
+def test_weather_tool_call(hf_repo: str, template_override: str | Tuple[str, str | None] | None):
     global server
     server.n_slots = 1
     server.jinja = True
     server.n_ctx = 8192
     server.n_predict = 512
     server.model_hf_repo = hf_repo
     server.model_hf_file = None
-    if template_override:
+    if isinstance(template_override, tuple):
         (template_hf_repo, template_variant) = template_override
         server.chat_template_file = f"../../../models/templates/{template_hf_repo.replace('/', '-') + ('-' + template_variant if template_variant else '')}.jinja"
         assert os.path.exists(server.chat_template_file), f"Template file {server.chat_template_file} does not exist. Run `python scripts/get_chat_template.py {template_hf_repo} {template_variant} > {server.chat_template_file}` to download the template."
+    elif isinstance(template_override, str):
+        server.chat_template = template_override
     server.start(timeout_seconds=TIMEOUT_SERVER_START)
     res = server.make_request("POST", "/chat/completions", data={
         "max_tokens": 256,
@@ -298,30 +340,52 @@ def test_weather_tool_call(hf_repo: str, template_override: Tuple[str, str | Non
 
 @pytest.mark.slow
 @pytest.mark.parametrize("expected_arguments_override,hf_repo,template_override", [
-    (None,                 "bartowski/gemma-2-2b-it-GGUF:Q4_K_M",              None),
     (None,                 "bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M",      None),
+    (None,                 "bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M",      "chatml"),
+
     (None,                 "bartowski/functionary-small-v3.2-GGUF:Q8_0",       ("meetkai-functionary-medium-v3.2", None)),
-    ('{"code":"print("}',  "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", None),
-    (None,                 "bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M",      ("meta-llama-Llama-3.2-3B-Instruct", None)),
+    (None,                 "bartowski/functionary-small-v3.2-GGUF:Q8_0",       "chatml"),
+
+    (None,                 "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", None),
+    ('{"code":"print("}',  "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", "chatml"),
+
+    ('{"code":"print("}',  "bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M",      ("meta-llama-Llama-3.2-3B-Instruct", None)),
+    (None,                 "bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M",      "chatml"),
+
     ('{"code":"print("}',  "bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M",      ("meta-llama-Llama-3.2-3B-Instruct", None)),
+    ('{"code":"print("}',  "bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M",      "chatml"),
+
     (None,                 "bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M",        None),
-    (None,                 "bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M",      ("NousResearch/Hermes-2-Pro-Llama-3-8B", "tool_use")),
-    (None,                 "bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M",   ("NousResearch-Hermes-3-Llama-3.1-8B", "tool_use")),
+    (None,                 "bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M",        "chatml"),
+
+    (None,                 "bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M",    ("NousResearch/Hermes-2-Pro-Llama-3-8B", "tool_use")),
+    (None,                 "bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M",    "chatml"),
+
+    (None,                 "bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M",      ("NousResearch-Hermes-3-Llama-3.1-8B", "tool_use")),
+    (None,                 "bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M",      "chatml"),
+
     (None,                 "bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", None),
+    (None,                 "bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", "chatml"),
+
+    # Note: gemma-2-2b-it knows itself as "model", not "assistant", so we don't test the ill-suited chatml on it.
+    (None,                 "bartowski/gemma-2-2b-it-GGUF:Q4_K_M",              None),
+
     # (None,                 "bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M", None),
 ])
-def test_hello_world_tool_call(expected_arguments_override: str | None, hf_repo: str, template_override: Tuple[str, str | None] | None):
+def test_hello_world_tool_call(expected_arguments_override: str | None, hf_repo: str, template_override: str | Tuple[str, str | None] | None):
     global server
     server.n_slots = 1
     server.jinja = True
     server.n_ctx = 8192
     server.n_predict = 128
     server.model_hf_repo = hf_repo
     server.model_hf_file = None
-    if template_override:
+    if isinstance(template_override, tuple):
         (template_hf_repo, template_variant) = template_override
         server.chat_template_file = f"../../../models/templates/{template_hf_repo.replace('/', '-') + ('-' + template_variant if template_variant else '')}.jinja"
         assert os.path.exists(server.chat_template_file), f"Template file {server.chat_template_file} does not exist. Run `python scripts/get_chat_template.py {template_hf_repo} {template_variant} > {server.chat_template_file}` to download the template."
+    elif isinstance(template_override, str):
+        server.chat_template = template_override
     server.start(timeout_seconds=TIMEOUT_SERVER_START)
     res = server.make_request("POST", "/chat/completions", data={
         "max_tokens": 256,