Skip to content

tool-call: command r7b fix for normal responses #11608

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Feb 4, 2025
Merged

tool-call: command r7b fix for normal responses #11608

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
568a4f5
fix command r7b normal response regex + add to server test
Feb 3, 2025
7e44fbe
test multiline non-tool-call responses in test-chat
Feb 3, 2025
91108c1
revert minor regex diff
Feb 3, 2025
2758680
Merge branch 'master' into c7rb-fix
Feb 4, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion common/chat.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -365,7 +365,7 @@ static common_chat_params common_chat_params_init_command_r7b(const common_chat_
return data;
}
static common_chat_msg common_chat_parse_command_r7b(const std::string & input) {
static std::regex response_regex("<\\|START_RESPONSE\\|>(.*?)<\\|END_RESPONSE\\|>");
static std::regex response_regex("<\\|START_RESPONSE\\|>([\\s\\S\\n\\r]*?)<\\|END_RESPONSE\\|>");
static std::regex thought_action_regex("<\\|START_THINKING\\|>([\\s\\S\\n\\r]*?)<\\|END_THINKING\\|><\\|START_ACTION\\|>([\\s\\S\\n\\r]*?)<\\|END_ACTION\\|>");
std::smatch match;

Expand Down
8 changes: 5 additions & 3 deletions examples/server/tests/unit/test_tool_call.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -273,6 +273,7 @@ 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/c4ai-command-r7b-12-2024-GGUF:Q4_K_M", ("CohereForAI/c4ai-command-r7b-12-2024", "tool_use")),
("bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", None),
("bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", "chatml"),

Expand Down Expand Up @@ -303,12 +304,13 @@ def test_completion_without_tool_call_slow(template_name: str, n_predict: int, t
# ("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: str | Tuple[str, str | None] | None):
def test_weather(hf_repo: str, template_override: Tuple[str, str | None] | None):
global server
n_predict = 512
server.n_slots = 1
server.jinja = True
server.n_ctx = 8192
server.n_predict = 512
server.n_predict = n_predict
server.model_hf_repo = hf_repo
server.model_hf_file = None
if isinstance(template_override, tuple):
Expand All @@ -319,7 +321,7 @@ def test_weather_tool_call(hf_repo: str, template_override: str | Tuple[str, str
server.chat_template = template_override
server.start(timeout_seconds=TIMEOUT_SERVER_START)
res = server.make_request("POST", "/chat/completions", data={
"max_tokens": 256,
"max_tokens": n_predict,
"messages": [
{"role": "user", "content": "What is the weather in Istanbul?"},
],
Expand Down
24 changes: 13 additions & 11 deletions tests/test-chat.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -289,7 +289,7 @@ static void test_template(const common_chat_template & tmpl, const std::vector<s
static void test_template_output_parsers() {
json text_message {
{ "role", "assistant" },
{ "content", "Hello, world!" },
{ "content", "Hello, world!\nWhat's up?" },
};
json tool_calls = json::array({{
{ "type", "function" },
Expand Down Expand Up @@ -379,7 +379,7 @@ static void test_template_output_parsers() {

common_chat_inputs inputs_no_tools;
inputs_no_tools.messages = {
{ { "role", "user" }, { "content", "Hey" } }
{ { "role", "user" }, { "content", "Hey\nThere" } }
};

common_chat_inputs inputs_tools = inputs_no_tools;
Expand Down Expand Up @@ -408,7 +408,8 @@ static void test_template_output_parsers() {
" {\"tool_call_id\": \"0\", \"tool_name\": \"special_function\", \"parameters\": {\"arg1\": 1}}\n"
"]<|END_ACTION|>");
test_template(tmpl, end_tokens, text_message, tools,
"<|START_RESPONSE|>Hello, world!<|END_RESPONSE|>",
"<|START_RESPONSE|>Hello, world!\n"
"What's up?<|END_RESPONSE|>",
/* expect_grammar_triggered= */ false);
}
{
Expand All @@ -428,7 +429,7 @@ static void test_template_output_parsers() {

assert_msg_equals(msg_from_json(text_message),
common_chat_parse("{\n"
" \"response\": \"Hello, world!\"\n"
" \"response\": \"Hello, world!\\nWhat's up?\"\n"
"}",
common_chat_params_init(tmpl, inputs_tools).format));
test_template(tmpl, end_tokens, tool_call_message_with_id, tools,
Expand All @@ -451,7 +452,7 @@ static void test_template_output_parsers() {

assert_equals(COMMON_CHAT_FORMAT_MISTRAL_NEMO, common_chat_params_init(tmpl, inputs_tools).format);

test_template(tmpl, end_tokens, text_message, tools, "Hello, world!", /* expect_grammar_triggered= */ false);
test_template(tmpl, end_tokens, text_message, tools, "Hello, world!\nWhat's up?", /* expect_grammar_triggered= */ false);
test_template(
tmpl, end_tokens, tool_call_message_with_id, tools,
"[TOOL_CALLS][{\"name\": \"special_function\", \"arguments\": {\"arg1\": 1}, \"id\": \"123456789\"}]");
Expand All @@ -476,7 +477,7 @@ static void test_template_output_parsers() {
inputs_tools)
.format);

test_template(tmpl, end_tokens, text_message, tools, "Hello, world!", /* expect_grammar_triggered= */ false);
test_template(tmpl, end_tokens, text_message, tools, "Hello, world!\nWhat's up?", /* expect_grammar_triggered= */ false);
test_template(tmpl, end_tokens, tool_call_message, tools,
"<tool_call>\n"
"{\"name\": \"special_function\", \"arguments\": {\"arg1\": 1}}\n"
Expand Down Expand Up @@ -516,7 +517,7 @@ static void test_template_output_parsers() {

assert_equals(COMMON_CHAT_FORMAT_LLAMA_3_X, common_chat_params_init(tmpl, inputs_tools).format);

test_template(tmpl, end_tokens, text_message, tools, "Hello, world!", /* expect_grammar_triggered= */ false);
test_template(tmpl, end_tokens, text_message, tools, "Hello, world!\nWhat's up?", /* expect_grammar_triggered= */ false);
test_template(tmpl, end_tokens, tool_call_message, tools,
"{\"name\": \"special_function\", \"parameters\": {\"arg1\": 1}}");
}
Expand All @@ -528,7 +529,7 @@ static void test_template_output_parsers() {
assert_equals(COMMON_CHAT_FORMAT_FUNCTIONARY_V3_1_LLAMA_3_1,
common_chat_params_init(tmpl, inputs_tools).format);

test_template(tmpl, end_tokens, text_message, tools, "Hello, world!", /* expect_grammar_triggered= */ false);
test_template(tmpl, end_tokens, text_message, tools, "Hello, world!\nWhat's up?", /* expect_grammar_triggered= */ false);
test_template(tmpl, end_tokens, tool_call_message, tools,
"<function=special_function>{\"arg1\": 1}</function>");
}
Expand All @@ -542,7 +543,8 @@ static void test_template_output_parsers() {

test_template(tmpl, end_tokens, text_message, {},
"all\n"
"Hello, world!",
"Hello, world!\n"
"What's up?",
/* expect_grammar_triggered= */ false);
test_template(tmpl, end_tokens, tool_call_message, tools,
"special_function\n"
Expand All @@ -555,7 +557,7 @@ static void test_template_output_parsers() {

assert_equals(COMMON_CHAT_FORMAT_FIREFUNCTION_V2, common_chat_params_init(tmpl, inputs_tools).format);

test_template(tmpl, end_tokens, text_message, tools, "Hello, world!", /* expect_grammar_triggered= */ false);
test_template(tmpl, end_tokens, text_message, tools, "Hello, world!\nWhat's up?", /* expect_grammar_triggered= */ false);
test_template(tmpl, end_tokens, tool_call_message, tools,
" functools[{\"name\": \"special_function\", \"arguments\": {\"arg1\": 1}}]");
}
Expand All @@ -566,7 +568,7 @@ static void test_template_output_parsers() {

assert_equals(COMMON_CHAT_FORMAT_DEEPSEEK_R1, common_chat_params_init(tmpl, inputs_tools).format);

test_template(tmpl, end_tokens, text_message, tools, "Hello, world!", /* expect_grammar_triggered= */ false);
test_template(tmpl, end_tokens, text_message, tools, "Hello, world!\nWhat's up?", /* expect_grammar_triggered= */ false);
test_template(tmpl, end_tokens, tool_call_message, tools,
"<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>function<｜tool▁sep｜>special_function\n"
"```json\n"
Expand Down
Loading