llama.cpp/tests/test_llama_chat_format.py

89 lines
3.3 KiB
Python
Raw Normal View History

import json
Integration of Jinja2 Templating (#875) * feat: Add support for jinja templating Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com> * fix: Refactor chat formatter and update interface for jinja templates - Simplify the `llama2_template` in `llama_jinja_format.py` by removing unnecessary line breaks for readability without affecting functionality. - Update `ChatFormatterInterface` constructor to accept a more generic `Optional[object]` type for the template parameter, enhancing flexibility. - Introduce a `template` property to `ChatFormatterInterface` for standardized access to the template string. - Replace `MetaSingleton` metaclass with `Singleton` for the `ChatFormatterFactory` to streamline the singleton implementation. These changes enhance code readability, maintain usability, and ensure consistency in the chat formatter's design pattern usage. * Add outline for Jinja2 templating integration documentation Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com> * Add jinja2 as a dependency with version range for Hugging Face transformers compatibility Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com> * Update jinja2 version constraint for mkdocs-material compatibility Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com> * Fix attribute name in AutoChatFormatter - Changed attribute name from `self._renderer` to `self._environment` --------- Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
2024-01-17 14:47:52 +00:00
2024-01-29 05:59:01 +00:00
import jinja2
from llama_cpp import (
ChatCompletionRequestUserMessage,
)
2024-01-29 05:59:01 +00:00
import llama_cpp.llama_types as llama_types
import llama_cpp.llama_chat_format as llama_chat_format
from llama_cpp.llama_chat_format import hf_tokenizer_config_to_chat_formatter
Integration of Jinja2 Templating (#875) * feat: Add support for jinja templating Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com> * fix: Refactor chat formatter and update interface for jinja templates - Simplify the `llama2_template` in `llama_jinja_format.py` by removing unnecessary line breaks for readability without affecting functionality. - Update `ChatFormatterInterface` constructor to accept a more generic `Optional[object]` type for the template parameter, enhancing flexibility. - Introduce a `template` property to `ChatFormatterInterface` for standardized access to the template string. - Replace `MetaSingleton` metaclass with `Singleton` for the `ChatFormatterFactory` to streamline the singleton implementation. These changes enhance code readability, maintain usability, and ensure consistency in the chat formatter's design pattern usage. * Add outline for Jinja2 templating integration documentation Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com> * Add jinja2 as a dependency with version range for Hugging Face transformers compatibility Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com> * Update jinja2 version constraint for mkdocs-material compatibility Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com> * Fix attribute name in AutoChatFormatter - Changed attribute name from `self._renderer` to `self._environment` --------- Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
2024-01-17 14:47:52 +00:00
2024-01-29 05:59:01 +00:00
def test_mistral_instruct():
chat_template = "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}"
chat_formatter = jinja2.Template(chat_template)
messages = [
llama_types.ChatCompletionRequestUserMessage(role="user", content="Instruction"),
llama_types.ChatCompletionRequestAssistantMessage(role="assistant", content="Model answer"),
llama_types.ChatCompletionRequestUserMessage(role="user", content="Follow-up instruction"),
]
response = llama_chat_format.format_mistral_instruct(
messages=messages,
)
reference = chat_formatter.render(
messages=messages,
bos_token="<s>",
eos_token="</s>",
)
assert response.prompt == reference
Integration of Jinja2 Templating (#875) * feat: Add support for jinja templating Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com> * fix: Refactor chat formatter and update interface for jinja templates - Simplify the `llama2_template` in `llama_jinja_format.py` by removing unnecessary line breaks for readability without affecting functionality. - Update `ChatFormatterInterface` constructor to accept a more generic `Optional[object]` type for the template parameter, enhancing flexibility. - Introduce a `template` property to `ChatFormatterInterface` for standardized access to the template string. - Replace `MetaSingleton` metaclass with `Singleton` for the `ChatFormatterFactory` to streamline the singleton implementation. These changes enhance code readability, maintain usability, and ensure consistency in the chat formatter's design pattern usage. * Add outline for Jinja2 templating integration documentation Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com> * Add jinja2 as a dependency with version range for Hugging Face transformers compatibility Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com> * Update jinja2 version constraint for mkdocs-material compatibility Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com> * Fix attribute name in AutoChatFormatter - Changed attribute name from `self._renderer` to `self._environment` --------- Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
2024-01-17 14:47:52 +00:00
mistral_7b_tokenizer_config = """{
"add_bos_token": true,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": null,
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false,
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}"
}"""
Integration of Jinja2 Templating (#875) * feat: Add support for jinja templating Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com> * fix: Refactor chat formatter and update interface for jinja templates - Simplify the `llama2_template` in `llama_jinja_format.py` by removing unnecessary line breaks for readability without affecting functionality. - Update `ChatFormatterInterface` constructor to accept a more generic `Optional[object]` type for the template parameter, enhancing flexibility. - Introduce a `template` property to `ChatFormatterInterface` for standardized access to the template string. - Replace `MetaSingleton` metaclass with `Singleton` for the `ChatFormatterFactory` to streamline the singleton implementation. These changes enhance code readability, maintain usability, and ensure consistency in the chat formatter's design pattern usage. * Add outline for Jinja2 templating integration documentation Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com> * Add jinja2 as a dependency with version range for Hugging Face transformers compatibility Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com> * Update jinja2 version constraint for mkdocs-material compatibility Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com> * Fix attribute name in AutoChatFormatter - Changed attribute name from `self._renderer` to `self._environment` --------- Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
2024-01-17 14:47:52 +00:00
def test_hf_tokenizer_config_str_to_chat_formatter():
tokenizer_config = json.loads(mistral_7b_tokenizer_config)
chat_formatter = hf_tokenizer_config_to_chat_formatter(
tokenizer_config
)
chat_formatter_respoonse = chat_formatter(
messages=[
ChatCompletionRequestUserMessage(role="user", content="Hello, world!"),
]
Integration of Jinja2 Templating (#875) * feat: Add support for jinja templating Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com> * fix: Refactor chat formatter and update interface for jinja templates - Simplify the `llama2_template` in `llama_jinja_format.py` by removing unnecessary line breaks for readability without affecting functionality. - Update `ChatFormatterInterface` constructor to accept a more generic `Optional[object]` type for the template parameter, enhancing flexibility. - Introduce a `template` property to `ChatFormatterInterface` for standardized access to the template string. - Replace `MetaSingleton` metaclass with `Singleton` for the `ChatFormatterFactory` to streamline the singleton implementation. These changes enhance code readability, maintain usability, and ensure consistency in the chat formatter's design pattern usage. * Add outline for Jinja2 templating integration documentation Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com> * Add jinja2 as a dependency with version range for Hugging Face transformers compatibility Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com> * Update jinja2 version constraint for mkdocs-material compatibility Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com> * Fix attribute name in AutoChatFormatter - Changed attribute name from `self._renderer` to `self._environment` --------- Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
2024-01-17 14:47:52 +00:00
)
assert chat_formatter_respoonse.prompt == ("<s>[INST] Hello, world! [/INST]</s>" "")