vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

sync: minja (#11641)

Browse source 
* `sync`: minja

182de30cda

https://github.com/google/minja/pull/46

https://github.com/google/minja/pull/45
This commit is contained in:
Olivier Chafik 2025-02-05 01:00:12 +00:00 • committed by GitHub
parent fd08255d0d
commit 9f4cc8f8d3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 233 additions and 58 deletions
Download patch file Download diff file Expand all files Collapse all files

45
common/chat.cpp
View file

@ -163,6 +163,28 @@ static void foreach_function(const json & tools, const std::function<void(const
}
}
static std::string apply(
const common_chat_template & tmpl,
const nlohmann::ordered_json & messages,
const nlohmann::ordered_json & tools,
bool add_generation_prompt,
const nlohmann::ordered_json & extra_context = nlohmann::ordered_json())
{
minja::chat_template_inputs tmpl_inputs;
tmpl_inputs.messages = messages;
tmpl_inputs.tools = tools;
tmpl_inputs.add_generation_prompt = add_generation_prompt;
tmpl_inputs.extra_context = extra_context;
// TODO: add flag to control date/time, if only for testing purposes.
// 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);
}
static common_chat_params common_chat_params_init_generic(const common_chat_template & tmpl, const struct common_chat_inputs & inputs) {
common_chat_params data;
@ -244,7 +266,7 @@ static common_chat_params common_chat_params_init_generic(const common_chat_temp
inputs.messages,
"Respond in JSON format, either with `tool_call` (a request to call tools) or with `response` reply to the user's request");
data.prompt = tmpl.apply(tweaked_messages, inputs.tools.empty() ? json() : inputs.tools, inputs.add_generation_prompt);
data.prompt = apply(tmpl, tweaked_messages, inputs.tools.empty() ? json() : inputs.tools, inputs.add_generation_prompt);
data.format = COMMON_CHAT_FORMAT_GENERIC;
return data;
}
@ -310,7 +332,7 @@ static common_chat_params common_chat_params_init_mistral_nemo(const common_chat
builder.add_rule("root", "\"[TOOL_CALLS]\" " + builder.add_schema("tool_calls", schema));
}, grammar_options);
data.grammar_triggers.push_back({"[TOOL_CALLS]", /* .at_start = */ true});
data.prompt = tmpl.apply(inputs.messages, inputs.tools.empty() ? json() : inputs.tools, inputs.add_generation_prompt);
data.prompt = apply(tmpl, inputs.messages, inputs.tools.empty() ? json() : inputs.tools, inputs.add_generation_prompt);
data.format = COMMON_CHAT_FORMAT_MISTRAL_NEMO;
return data;
}
@ -360,7 +382,7 @@ static common_chat_params common_chat_params_init_command_r7b(const common_chat_
"<|END_THINKING|>",
"<|END_ACTION|>",
};
data.prompt = tmpl.apply(inputs.messages, inputs.tools.empty() ? json() : inputs.tools, inputs.add_generation_prompt);
data.prompt = apply(tmpl, inputs.messages, inputs.tools.empty() ? json() : inputs.tools, inputs.add_generation_prompt);
data.format = COMMON_CHAT_FORMAT_COMMAND_R7B;
return data;
}
@ -477,7 +499,7 @@ static common_chat_params common_chat_params_init_llama_3_1_tool_calls(const com
builder.add_rule("root", string_join(tool_rules, " | "));
}, grammar_options);
data.additional_stops.push_back("<|eom_id|>");
data.prompt = tmpl.apply(inputs.messages, inputs.tools.empty() ? json() : inputs.tools, inputs.add_generation_prompt, {
data.prompt = apply(tmpl, inputs.messages, inputs.tools.empty() ? json() : inputs.tools, inputs.add_generation_prompt, {
{"tools_in_user_message", false},
{"builtin_tools", builtin_tools.empty() ? json() : builtin_tools},
});
@ -542,7 +564,8 @@ static common_chat_params common_chat_params_init_deepseek_r1(const common_chat_
};
builder.add_rule("root", "\"<｜tool▁calls▁begin｜>\" (" + string_join(tool_rules, " | ") + ")" + (inputs.parallel_tool_calls ? "*" : "") + " space");
}, grammar_options);
data.prompt = tmpl.apply(inputs.messages, inputs.tools.empty() ? json() : inputs.tools, inputs.add_generation_prompt);
auto prompt = apply(tmpl, inputs.messages, inputs.tools.empty() ? json() : inputs.tools, inputs.add_generation_prompt);
data.prompt = prompt;
data.format = COMMON_CHAT_FORMAT_DEEPSEEK_R1;
return data;
}
@ -556,10 +579,10 @@ static common_chat_msg common_chat_parse_deepseek_r1(const std::string & input)
static common_chat_params common_chat_params_init_firefunction_v2(const common_chat_template & tmpl, const struct common_chat_inputs & inputs) {
fprintf(stderr, "%s\n", __func__);
common_chat_params data;
data.prompt = tmpl.apply(inputs.messages, /* tools= */ nullptr, inputs.add_generation_prompt, {
data.prompt = apply(tmpl, inputs.messages, /* tools= */ nullptr, inputs.add_generation_prompt, {
{"datetime", "Jan 29 2025 13:00:00 GMT"},
{"functions", json(inputs.tools.empty() ? "" : inputs.tools.dump(2))},
}, /* adjust_inputs= */ false);
});
if (!inputs.tools.is_null() && !inputs.tools.empty()) {
data.grammar_lazy = inputs.tool_choice != "required";
data.grammar = build_grammar([&](const common_grammar_builder & builder) {
@ -603,7 +626,7 @@ static common_chat_params common_chat_params_init_functionary_v3_2(const common_
// >>>all\nlet's call functions>>>fn1\n{"arg1": 1...}\n>>>fn2\n{"arg1": 1...}...
// Using ">>>f1\n", ">>>f2\n"... as trigger words for the grammar
common_chat_params data;
data.prompt = tmpl.apply(inputs.messages, inputs.tools.empty() ? json() : inputs.tools, inputs.add_generation_prompt);
data.prompt = apply(tmpl, inputs.messages, inputs.tools.empty() ? json() : inputs.tools, inputs.add_generation_prompt);
data.format = COMMON_CHAT_FORMAT_FUNCTIONARY_V3_2;
if (!inputs.tools.is_null() && !inputs.tools.empty()) {
data.grammar_lazy = inputs.tool_choice != "required";
@ -730,7 +753,7 @@ static common_chat_params common_chat_params_init_functionary_v3_1_llama_3_1(con
data.grammar_triggers.push_back({"<function=", /* .at_start = */ false});
}, grammar_options);
data.prompt = tmpl.apply(inputs.messages, inputs.tools.empty() ? json() : inputs.tools, inputs.add_generation_prompt);
data.prompt = apply(tmpl, inputs.messages, inputs.tools.empty() ? json() : inputs.tools, inputs.add_generation_prompt);
// TODO: if (has_raw_python)
data.format = COMMON_CHAT_FORMAT_FUNCTIONARY_V3_1_LLAMA_3_1;
return data;
@ -785,7 +808,7 @@ static common_chat_params common_chat_params_init_hermes_2_pro(const common_chat
data.preserved_tokens = { "</tool_call>" };
}, grammar_options);
data.prompt = tmpl.apply(inputs.messages, inputs.tools.empty() ? json() : inputs.tools, inputs.add_generation_prompt);
data.prompt = apply(tmpl, inputs.messages, inputs.tools.empty() ? json() : inputs.tools, inputs.add_generation_prompt);
data.format = COMMON_CHAT_FORMAT_HERMES_2_PRO;
return data;
}
@ -846,7 +869,7 @@ static common_chat_msg common_chat_parse_hermes_2_pro(const std::string & input)
static common_chat_params common_chat_params_init_without_tools(const common_chat_template & tmpl, const struct common_chat_inputs & inputs) {
common_chat_params data;
data.prompt = tmpl.apply(inputs.messages, inputs.tools.empty() ? json() : inputs.tools, inputs.add_generation_prompt);
data.prompt = apply(tmpl, inputs.messages, inputs.tools.empty() ? json() : inputs.tools, inputs.add_generation_prompt);
data.format = COMMON_CHAT_FORMAT_CONTENT_ONLY;
data.grammar_lazy = false;
if (!inputs.json_schema.is_null()) {