koboldcpp/kcpp_adapters/AutoGuess.json
kallewoof ff8f156fa0
AutoGuess tests (#1650)
* whitespace

* AutoGuess remove dot suffix in names

* .gitignore update

* test: added autoguess test suite

* github workflow to run autoguess test when appropriate

* git clone unavailable tokenizer configs rather than committing to repo

* fix link to included tokenizer configs

* skip storing downloaded tokenizer configs

* typo

* minor fixes

* clean-up

* limit workflow to trigger from experimental branch

---------

Co-authored-by: Concedo <39025047+LostRuins@users.noreply.github.com>
2025-07-25 19:21:00 +08:00

225 lines
7.7 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

[
{
"search": ["<|im_start|>assistant", "<|im_end|>", "<|im_sep|>"],
"name": "ChatML (Phi 4)",
"adapter": {
"system_start": "<|im_start|>system<|im_sep|>",
"system_end": "<|im_end|>",
"user_start": "<|im_start|>user<|im_sep|>",
"user_end": "<|im_end|>",
"assistant_start": "<|im_start|>assistant<|im_sep|>",
"assistant_end": "<|im_end|>"
}
}, {
"search": ["<|im_start|>assistant", "<|im_end|>", "You are provided with function signatures within <tools>"],
"name": "ChatML (Qwen 2.5 based)",
"adapter": {
"system_start": "<|im_start|>system\n",
"system_end": "<|im_end|>\n",
"user_start": "<|im_start|>user\n",
"user_end": "<|im_end|>\n",
"assistant_start": "<|im_start|>assistant\n",
"assistant_end": "<|im_end|>\n",
"tools_start": "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n",
"tools_end": "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n"
}
}, {
"search": ["<|im_user|>user<|im_middle|>", "<|im_assistant|>assistant<|im_middle|>", "<|im_end|>"],
"name": "ChatML (Kimi)",
"adapter": {
"system_start": "<|im_system|>system<|im_middle|>",
"system_end": "<|im_end|>",
"user_start": "<|im_user|>user<|im_middle|>",
"user_end": "<|im_end|>",
"assistant_start": "<|im_assistant|>assistant<|im_middle|>",
"assistant_end": "<|im_end|>"
}
}, {
"search": ["System role not supported", "<start_of_turn>"],
"name": "Google Gemma 2",
"adapter": {
"system_start": "<start_of_turn>user\n",
"system_end": "<end_of_turn>\n",
"user_start": "<start_of_turn>user\n",
"user_end": "<end_of_turn>\n",
"assistant_start": "<start_of_turn>model\n",
"assistant_end": "<end_of_turn>\n"
}
}, {
"search": ["<start_of_image>", "<start_of_turn>", "<end_of_turn>"],
"name": "Google Gemma 3",
"adapter": {
"system_start": "<start_of_turn>user\n",
"system_end": "<end_of_turn>\n",
"user_start": "<start_of_turn>user\n",
"user_end": "<end_of_turn>\n",
"assistant_start": "<start_of_turn>model\n",
"assistant_end": "<end_of_turn>\n"
}
}, {
"search": ["<image_soft_token>", "<start_of_turn>model", "<end_of_turn>"],
"name": "Google Gemma 3n",
"adapter": {
"system_start": "<start_of_turn>user\n",
"system_end": "<end_of_turn>\n",
"user_start": "<start_of_turn>user\n",
"user_end": "<end_of_turn>\n",
"assistant_start": "<start_of_turn>model\n",
"assistant_end": "<end_of_turn>\n"
}
},{
"search": ["<|start_header_id|>assistant<|end_header_id|>"],
"name": "Llama 3.x",
"adapter": {
"system_start": "<|start_header_id|>system<|end_header_id|>\n\n",
"system_end": "<|eot_id|>",
"user_start": "<|start_header_id|>user<|end_header_id|>\n\n",
"user_end": "<|eot_id|>",
"assistant_start": "<|start_header_id|>assistant<|end_header_id|>\n\n",
"assistant_end": "<|eot_id|>"
}
}, {
"search": ["<|header_start|>assistant<|header_end|>"],
"name": "Llama 4",
"adapter": {
"system_start": "<|header_start|>system<|header_end|>\n\n",
"system_end": "<|eot|>",
"user_start": "<|header_start|>user<|header_end|>\n\n",
"user_end": "<|eot|>",
"assistant_start": "<|header_start|>assistant<|header_end|>\n\n",
"assistant_end": "<|eot|>"
}
}, {
"search": ["[/INST]", "[SYSTEM_PROMPT]"],
"name": "Mistral V7 (with system prompt)",
"adapter": {
"system_start": "[SYSTEM_PROMPT]",
"system_end": "[/SYSTEM_PROMPT]",
"user_start": "[INST]",
"user_end": "",
"assistant_start": "[/INST]",
"assistant_end": "</s>"
}
}, {
"search": ["[/INST]", "\"[INST] \" + system_message"],
"name": "Mistral V3",
"adapter": {
"system_start": "[INST] ",
"system_end": "[/INST]",
"user_start": "[INST] ",
"user_end": "",
"assistant_start": "[/INST]",
"assistant_end": "</s>"
}
}, {
"search": ["[gMASK]<sop>"],
"name": "GLM-4",
"adapter": {
"system_start": "<|system|>\n",
"system_end": "",
"user_start": "<|user|>\n",
"user_end": "",
"assistant_start": "<|assistant|>\n",
"assistant_end": ""
}
}, {
"search": ["<|system|>", "<|user|>"],
"name": "Phi 3.5",
"adapter": {
"system_start": "<|system|>\n",
"system_end": "<|end|>\n",
"user_start": "<|user|>\n",
"user_end": "<|end|>\n",
"assistant_start": "<|assistant|>\n",
"assistant_end": "<|end|>\n"
}
}, {
"search": ["'<|' + message['role'] + '|>'"],
"name": "Phi 4 (mini)",
"adapter": {
"system_start": "<|system|>\n",
"system_end": "<|end|>\n",
"user_start": "<|user|>\n",
"user_end": "<|end|>\n",
"assistant_start": "<|assistant|>\n",
"assistant_end": "<|end|>\n"
}
}, {
"search": ["<|START_OF_TURN_TOKEN|>"],
"name": "Cohere (Aya Expanse 32B based)",
"adapter": {
"system_start": "<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>",
"system_end": "<|END_OF_TURN_TOKEN|>",
"user_start": "<|START_OF_TURN_TOKEN|><|USER_TOKEN|>",
"user_end": "<|END_OF_TURN_TOKEN|>",
"assistant_start": "<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>",
"assistant_end": "<|END_OF_TURN_TOKEN|>"
}
}, {
"search": ["<User>"],
"name": "DeepSeek V2.5",
"adapter": {
"system_start": "",
"system_end": "",
"user_start": "<User>",
"user_end": "",
"assistant_start": "<Assistant>",
"assistant_end": "<end▁of▁sentence>"
}
}, {
"search": ["<|bom|>","is_last_checked_defined"],
"name": "Jamba",
"adapter": {
"system_start": "<|bom|><|system|>",
"system_end": "<|eom|>",
"user_start": "<|bom|><|user|>",
"user_end": "<|eom|>",
"assistant_start": "<|bom|><|assistant|>",
"assistant_end": "<|eom|>"
}
}, {
"search": ["<|userprompt|>", "<|endofuserprompt|>", "<|response|>", "<|endofresponse|>"],
"name": "Dots",
"adapter": {
"system_start": "<|system|>\n",
"system_end": "<|endofsystem|>\n",
"user_start": "<|userprompt|>\n",
"user_end": "<|endofuserprompt|>\n",
"assistant_start": "<|response|>\n",
"assistant_end": "<|endofresponse|>\n"
}
}, {
"search": ["rwkv-world"],
"name": "RWKV World",
"adapter": {
"system_start": "",
"system_end": "\n\n",
"user_start": "USER: ",
"user_end": "\n",
"assistant_start": "ASSISTANT: ",
"assistant_end": "</s>\n"
}
}, {
"search": ["[/INST]"],
"name": "Mistral (Generic)",
"adapter": {
"system_start": "[INST]",
"system_end": "[/INST]\n",
"user_start": "[INST]",
"user_end": "",
"assistant_start": "[/INST]\n",
"assistant_end": "</s>"
}
}, {
"search": ["<|im_start|>assistant", "<|im_end|>"],
"name": "ChatML (Generic)",
"adapter": {
"system_start": "<|im_start|>system\n",
"system_end": "<|im_end|>\n",
"user_start": "<|im_start|>user\n",
"user_end": "<|im_end|>\n",
"assistant_start": "<|im_start|>assistant\n",
"assistant_end": "<|im_end|>\n"
}
}
]