mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-08-01 07:30:48 -05:00
6137c325a1
* chat : add Granite 4.0 chat template with correct tool_call role mapping Introduce `LLM_CHAT_TEMPLATE_GRANITE_4_0` alongside the existing Granite 3.x template (renamed `LLM_CHAT_TEMPLATE_GRANITE_3_X`). The Granite 4.0 Jinja template uses `<tool_call>` XML tags and maps the `assistant_tool_call` role to `<|start_of_role|>assistant<|end_of_role|><|tool_call|>`. Without a matching C++ handler, the fallback path emits the literal role `assistant_tool_call` which the model does not recognize, breaking tool calling when `--jinja` is not used. Changes: - Rename `LLM_CHAT_TEMPLATE_GRANITE` to `LLM_CHAT_TEMPLATE_GRANITE_3_X` (preserves existing 3.x behavior unchanged) - Add `LLM_CHAT_TEMPLATE_GRANITE_4_0` enum, map entry, and handler - Detection: `<|start_of_role|>` + (`<tool_call>` or `<tools>`) → 4.0, otherwise → 3.x - Add production Granite 4.0 Jinja template - Add tests for both 3.x and 4.0 template paths (C++ and Jinja) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * Code review: follow standard format and use common logic in test-chat-template.cpp * Rename custom_conversation variable for extra_conversation to give it a more meaningful name --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
74 lines
2.2 KiB
C++
74 lines
2.2 KiB
C++
#pragma once
|
|
|
|
#include <string>
|
|
#include <vector>
|
|
#include <cstdint>
|
|
|
|
enum llm_chat_template {
|
|
LLM_CHAT_TEMPLATE_CHATML,
|
|
LLM_CHAT_TEMPLATE_LLAMA_2,
|
|
LLM_CHAT_TEMPLATE_LLAMA_2_SYS,
|
|
LLM_CHAT_TEMPLATE_LLAMA_2_SYS_BOS,
|
|
LLM_CHAT_TEMPLATE_LLAMA_2_SYS_STRIP,
|
|
LLM_CHAT_TEMPLATE_MISTRAL_V1,
|
|
LLM_CHAT_TEMPLATE_MISTRAL_V3,
|
|
LLM_CHAT_TEMPLATE_MISTRAL_V3_TEKKEN,
|
|
LLM_CHAT_TEMPLATE_MISTRAL_V7,
|
|
LLM_CHAT_TEMPLATE_MISTRAL_V7_TEKKEN,
|
|
LLM_CHAT_TEMPLATE_PHI_3,
|
|
LLM_CHAT_TEMPLATE_PHI_4,
|
|
LLM_CHAT_TEMPLATE_FALCON_3,
|
|
LLM_CHAT_TEMPLATE_ZEPHYR,
|
|
LLM_CHAT_TEMPLATE_MONARCH,
|
|
LLM_CHAT_TEMPLATE_GEMMA,
|
|
LLM_CHAT_TEMPLATE_ORION,
|
|
LLM_CHAT_TEMPLATE_OPENCHAT,
|
|
LLM_CHAT_TEMPLATE_VICUNA,
|
|
LLM_CHAT_TEMPLATE_VICUNA_ORCA,
|
|
LLM_CHAT_TEMPLATE_DEEPSEEK,
|
|
LLM_CHAT_TEMPLATE_DEEPSEEK_2,
|
|
LLM_CHAT_TEMPLATE_DEEPSEEK_3,
|
|
LLM_CHAT_TEMPLATE_DEEPSEEK_OCR,
|
|
LLM_CHAT_TEMPLATE_COMMAND_R,
|
|
LLM_CHAT_TEMPLATE_LLAMA_3,
|
|
LLM_CHAT_TEMPLATE_CHATGLM_3,
|
|
LLM_CHAT_TEMPLATE_CHATGLM_4,
|
|
LLM_CHAT_TEMPLATE_GLMEDGE,
|
|
LLM_CHAT_TEMPLATE_MINICPM,
|
|
LLM_CHAT_TEMPLATE_EXAONE_3,
|
|
LLM_CHAT_TEMPLATE_EXAONE_4,
|
|
LLM_CHAT_TEMPLATE_EXAONE_MOE,
|
|
LLM_CHAT_TEMPLATE_RWKV_WORLD,
|
|
LLM_CHAT_TEMPLATE_GRANITE_3_X,
|
|
LLM_CHAT_TEMPLATE_GRANITE_4_0,
|
|
LLM_CHAT_TEMPLATE_GIGACHAT,
|
|
LLM_CHAT_TEMPLATE_MEGREZ,
|
|
LLM_CHAT_TEMPLATE_YANDEX,
|
|
LLM_CHAT_TEMPLATE_BAILING,
|
|
LLM_CHAT_TEMPLATE_BAILING_THINK,
|
|
LLM_CHAT_TEMPLATE_BAILING2,
|
|
LLM_CHAT_TEMPLATE_LLAMA4,
|
|
LLM_CHAT_TEMPLATE_SMOLVLM,
|
|
LLM_CHAT_TEMPLATE_DOTS1,
|
|
LLM_CHAT_TEMPLATE_HUNYUAN_MOE,
|
|
LLM_CHAT_TEMPLATE_OPENAI_MOE,
|
|
LLM_CHAT_TEMPLATE_HUNYUAN_DENSE,
|
|
LLM_CHAT_TEMPLATE_KIMI_K2,
|
|
LLM_CHAT_TEMPLATE_SEED_OSS,
|
|
LLM_CHAT_TEMPLATE_GROK_2,
|
|
LLM_CHAT_TEMPLATE_PANGU_EMBED,
|
|
LLM_CHAT_TEMPLATE_SOLAR_OPEN,
|
|
LLM_CHAT_TEMPLATE_UNKNOWN,
|
|
};
|
|
|
|
struct llama_chat_message;
|
|
|
|
llm_chat_template llm_chat_template_from_str(const std::string & name);
|
|
|
|
llm_chat_template llm_chat_detect_template(const std::string & tmpl);
|
|
|
|
int32_t llm_chat_apply_template(
|
|
llm_chat_template tmpl,
|
|
const std::vector<const llama_chat_message *> & chat,
|
|
std::string & dest, bool add_ass);
|