model : add EXAONE MoE (#18543)
* Add EXAONE MoE implementations Co-authored-by: Junwon Hwang <nuclear1221@gmail.com> * Address PR feedback * Address PR feedback * [WIP] Add MTP for EXAONE-MoE * Address PR feedback * Address PR feedback * Address PR feedback * Address PR feedback * Address PR feedback * Address PR feedback * Address PR feedback --------- Co-authored-by: LG-AI-EXAONE <exaonemodels@lgresearch.ai>
This commit is contained in:
@@ -1403,6 +1403,118 @@ static void common_chat_parse_solar_open(common_chat_msg_parser & builder) {
|
||||
builder.add_content(builder.consume_rest());
|
||||
}
|
||||
|
||||
static void common_chat_parse_exaone_moe_content(common_chat_msg_parser & builder) {
|
||||
// 1) <tool_call>{ "name": "...", "arguments": {...} }</tool_call>
|
||||
// 2) <tool_call>{ "id": "...", "type": "function", "function": { "name": "...", "arguments": {...} } }</tool_call>
|
||||
static const common_regex tool_call_open(R"(<tool_call[^>]*>)");
|
||||
|
||||
if (!builder.syntax().parse_tool_calls) {
|
||||
LOG_DBG("%s: not parse_tool_calls\n", __func__);
|
||||
builder.add_content(builder.consume_rest());
|
||||
return;
|
||||
}
|
||||
|
||||
LOG_DBG("%s: parse_tool_calls\n", __func__);
|
||||
|
||||
// Find all <tool_call></tool_call> blocks
|
||||
while (auto first = builder.try_find_regex(tool_call_open, std::string::npos, /* add_prelude_to_content= */ true)) {
|
||||
builder.move_to(first->groups[0].end);
|
||||
builder.consume_spaces();
|
||||
|
||||
builder.try_consume_literal("```json");
|
||||
builder.try_consume_literal("```");
|
||||
builder.consume_spaces();
|
||||
|
||||
// Consume JSON object
|
||||
auto data = builder.consume_json();
|
||||
|
||||
builder.consume_spaces();
|
||||
builder.try_consume_literal("```");
|
||||
builder.consume_spaces();
|
||||
|
||||
if (!builder.try_consume_literal("</tool_call>")) {
|
||||
throw common_chat_msg_partial_exception("incomplete tool call");
|
||||
}
|
||||
builder.consume_spaces();
|
||||
|
||||
// Extract name and arguments
|
||||
std::string name;
|
||||
std::string id;
|
||||
nlohmann::ordered_json arguments;
|
||||
|
||||
const auto extract_args = [&](const nlohmann::ordered_json & obj) -> bool {
|
||||
if (!obj.contains("name") || !obj.contains("arguments")) {
|
||||
return false;
|
||||
}
|
||||
name = obj.at("name").get<std::string>();
|
||||
arguments = obj.at("arguments");
|
||||
if (obj.contains("id") && obj.at("id").is_string()) {
|
||||
id = obj.at("id").get<std::string>();
|
||||
}
|
||||
return true;
|
||||
};
|
||||
|
||||
if (!extract_args(data.json)) {
|
||||
if (data.json.contains("function") && data.json.at("function").is_object()) {
|
||||
auto fn = data.json.at("function");
|
||||
extract_args(fn);
|
||||
if (id.empty() && data.json.contains("id") && data.json.at("id").is_string()) {
|
||||
id = data.json.at("id").get<std::string>();
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// If name is empty, treat the JSON object as content
|
||||
if (name.empty()) {
|
||||
LOG_DBG("%s: tool call missing name, treating as content\n", __func__);
|
||||
builder.add_content(data.json.dump());
|
||||
continue;
|
||||
}
|
||||
|
||||
std::string args_str = arguments.dump();
|
||||
if (!builder.add_tool_call(name, id, args_str)) {
|
||||
throw common_chat_msg_partial_exception("incomplete tool call");
|
||||
}
|
||||
}
|
||||
|
||||
builder.add_content(builder.consume_rest());
|
||||
}
|
||||
|
||||
static void common_chat_parse_exaone_moe(common_chat_msg_parser & builder) {
|
||||
LOG_DBG("%s: parsing exaone_moe\n", __func__);
|
||||
// EXAONE MoE outputs reasoning content between "<think>" and "</think>" tags, followed by regular content
|
||||
// First try to parse using the standard reasoning parsing method
|
||||
LOG_DBG("%s: thinking_forced_open: %s\n", __func__, std::to_string(builder.syntax().thinking_forced_open).c_str());
|
||||
|
||||
auto start_pos = builder.pos();
|
||||
auto found_end_think = builder.try_find_literal("</think>");
|
||||
builder.move_to(start_pos);
|
||||
|
||||
if (builder.syntax().thinking_forced_open && !builder.is_partial() && !found_end_think) {
|
||||
LOG_DBG("%s: no end_think, not partial, adding content\n", __func__);
|
||||
common_chat_parse_exaone_moe_content(builder);
|
||||
} else if (builder.try_parse_reasoning("<think>", "</think>")) {
|
||||
// If reasoning was parsed successfully, the remaining content is regular content
|
||||
LOG_DBG("%s: parsed reasoning, adding content\n", __func__);
|
||||
common_chat_parse_exaone_moe_content(builder);
|
||||
} else {
|
||||
if (builder.syntax().reasoning_format == COMMON_REASONING_FORMAT_NONE) {
|
||||
LOG_DBG("%s: reasoning_format none, adding content\n", __func__);
|
||||
common_chat_parse_exaone_moe_content(builder);
|
||||
return;
|
||||
}
|
||||
// If no reasoning tags found, check if we should treat everything as reasoning
|
||||
if (builder.syntax().thinking_forced_open) {
|
||||
// If thinking is forced open but no tags found, treat everything as reasoning
|
||||
LOG_DBG("%s: thinking_forced_open, adding reasoning content\n", __func__);
|
||||
builder.add_reasoning_content(builder.consume_rest());
|
||||
} else {
|
||||
LOG_DBG("%s: no thinking_forced_open, adding content\n", __func__);
|
||||
common_chat_parse_exaone_moe_content(builder);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
static void common_chat_parse_content_only(common_chat_msg_parser & builder) {
|
||||
builder.try_parse_reasoning("<think>", "</think>");
|
||||
builder.add_content(builder.consume_rest());
|
||||
@@ -1490,6 +1602,9 @@ static void common_chat_parse(common_chat_msg_parser & builder) {
|
||||
case COMMON_CHAT_FORMAT_SOLAR_OPEN:
|
||||
common_chat_parse_solar_open(builder);
|
||||
break;
|
||||
case COMMON_CHAT_FORMAT_EXAONE_MOE:
|
||||
common_chat_parse_exaone_moe(builder);
|
||||
break;
|
||||
default:
|
||||
throw std::runtime_error(std::string("Unsupported format: ") + common_chat_format_name(builder.syntax().format));
|
||||
}
|
||||
|
||||
@@ -670,6 +670,7 @@ const char * common_chat_format_name(common_chat_format format) {
|
||||
case COMMON_CHAT_FORMAT_APRIEL_1_5: return "Apriel 1.5";
|
||||
case COMMON_CHAT_FORMAT_XIAOMI_MIMO: return "Xiaomi MiMo";
|
||||
case COMMON_CHAT_FORMAT_SOLAR_OPEN: return "Solar Open";
|
||||
case COMMON_CHAT_FORMAT_EXAONE_MOE: return "EXAONE MoE";
|
||||
case COMMON_CHAT_FORMAT_PEG_SIMPLE: return "peg-simple";
|
||||
case COMMON_CHAT_FORMAT_PEG_NATIVE: return "peg-native";
|
||||
case COMMON_CHAT_FORMAT_PEG_CONSTRUCTED: return "peg-constructed";
|
||||
@@ -2539,6 +2540,65 @@ static common_chat_params common_chat_params_init_solar_open(const common_chat_t
|
||||
return data;
|
||||
}
|
||||
|
||||
static common_chat_params common_chat_params_init_exaone_moe(const common_chat_template & tmpl, const struct templates_params & inputs) {
|
||||
common_chat_params data;
|
||||
|
||||
data.prompt = apply(tmpl, inputs);
|
||||
data.format = COMMON_CHAT_FORMAT_EXAONE_MOE;
|
||||
if (string_ends_with(data.prompt, "<think>\n")) {
|
||||
if (!inputs.enable_thinking) {
|
||||
data.prompt += "</think>\n\n";
|
||||
} else {
|
||||
data.thinking_forced_open = true;
|
||||
}
|
||||
}
|
||||
|
||||
if (inputs.tools.is_array() && !inputs.tools.empty()) {
|
||||
data.grammar_lazy = inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_REQUIRED && inputs.json_schema.is_null();
|
||||
data.grammar = build_grammar([&](const common_grammar_builder & builder) {
|
||||
std::vector<std::string> tool_rules;
|
||||
foreach_function(inputs.tools, [&](const json & tool) {
|
||||
const auto & function = tool.at("function");
|
||||
std::string name = function.at("name");
|
||||
auto parameters = function.at("parameters");
|
||||
builder.resolve_refs(parameters);
|
||||
// Expect: <tool_call>{"name": "<name>", "arguments": {...}}</tool_call>
|
||||
tool_rules.push_back(builder.add_rule(
|
||||
name + "-call",
|
||||
"\"<tool_call>\" space " +
|
||||
builder.add_schema(name + "-obj", json{
|
||||
{"type", "object"},
|
||||
{"properties", {
|
||||
{"name", json{{"const", name}}},
|
||||
{"arguments", parameters},
|
||||
}},
|
||||
{"required", json::array({"name", "arguments"})},
|
||||
}) +
|
||||
" space \"</tool_call>\" space"));
|
||||
});
|
||||
|
||||
auto tool_call = builder.add_rule("tool_call", string_join(tool_rules, " | "));
|
||||
builder.add_rule("root",
|
||||
std::string(data.thinking_forced_open ? "( \"</think>\" space )? " : "") +
|
||||
(inputs.parallel_tool_calls ? "(" + tool_call + ")+" : tool_call));
|
||||
|
||||
data.grammar_triggers.push_back({
|
||||
COMMON_GRAMMAR_TRIGGER_TYPE_PATTERN_FULL,
|
||||
std::string(data.thinking_forced_open ? "[\\s\\S]*?(</think>\\s*)?" : "") +
|
||||
"(<tool_call>)[\\s\\S]*"
|
||||
});
|
||||
data.preserved_tokens = {
|
||||
"<think>",
|
||||
"</think>",
|
||||
"<tool_call>",
|
||||
"</tool_call>",
|
||||
};
|
||||
});
|
||||
}
|
||||
|
||||
return data;
|
||||
}
|
||||
|
||||
static common_chat_params common_chat_params_init_without_tools(const common_chat_template & tmpl, const struct templates_params & inputs) {
|
||||
common_chat_params data;
|
||||
data.prompt = apply(tmpl, inputs);
|
||||
@@ -2709,6 +2769,13 @@ static common_chat_params common_chat_templates_apply_jinja(
|
||||
return common_chat_params_init_xiaomi_mimo(tmpl, params);
|
||||
}
|
||||
|
||||
// EXAONE MoE format detection
|
||||
if (src.find("<tool_call>") != std::string::npos &&
|
||||
src.find("<tool_result>") != std::string::npos &&
|
||||
src.find("<|tool_declare|>") != std::string::npos) {
|
||||
return common_chat_params_init_exaone_moe(tmpl, params);
|
||||
}
|
||||
|
||||
// Hermes 2/3 Pro, Qwen 2.5 Instruct (w/ tools)
|
||||
if (src.find("<tool_call>") != std::string::npos && params.json_schema.is_null()) {
|
||||
return common_chat_params_init_hermes_2_pro(tmpl, params);
|
||||
|
||||
@@ -125,6 +125,7 @@ enum common_chat_format {
|
||||
COMMON_CHAT_FORMAT_APRIEL_1_5,
|
||||
COMMON_CHAT_FORMAT_XIAOMI_MIMO,
|
||||
COMMON_CHAT_FORMAT_SOLAR_OPEN,
|
||||
COMMON_CHAT_FORMAT_EXAONE_MOE,
|
||||
|
||||
// These are intended to be parsed by the PEG parser
|
||||
COMMON_CHAT_FORMAT_PEG_SIMPLE,
|
||||
|
||||
Reference in New Issue
Block a user