chat_templates
This is a repository that includes proper chat templates (or input formats) for instruction-tuned large language models (LLMs), to support transformers's chat_template feature. If you are interested to include more chat templates, feel free to open a pull request
If you find this repo useful, please kindly cite it:
@misc{zheng-2024-chat-templates,
author = {Zheng, Chujie},
title = {Chat Templates for HuggingFace Large Language Models},
year = {2024},
howpublished = {\url{https://github.com/chujiezheng/chat_templates}}
}Updates
- [07/2024] Added support for Meta's Llama-3.1 models
- [06/2024] Added support for Google's Gemma-2 models
- [05/2024] Added support for Nvidia's ChatQA models
- [04/2024] Added support for Microsoft's Phi-3 models
- [04/2024] Added support for Meta's Llama-3 models
- [02/2024] Added support for Google's Gemma models
- [02/2024] Added usage explanation for generation_configs
- [01/2024] Added support for Alibaba's Qwen2 models
What are Contained in This Repo?
-
chat_templatescontains the jinja files of collected chat templates, which can be directly replaced in the Huggingface tokenizers -
generation_configscontains the corresponding json configs used for controlling the ending of response generations. Specially, thestop_token_idsshould be directly passed into thegeneratemethod by theeos_token_idargument
Usage Examples
Important NOTE: As mentioned in this issue, the messages should contain at least one user message. It is strongly not recommented to pass only the system message, as there may result in unexpected outputs (because the models are not trained in this way).
Example 1: Meta-Llama-3-8B-Instruct
This example may check if the jinja file is correctly implemented. ```python from transformers import AutoTokenizer toker = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct", token="YOUR_OWN_TOKEN") messages = [ {'role': 'system', 'content': 'This is a system prompt.'}, {'role': 'user', 'content': 'This is the first user input.'}, {'role': 'assistant', 'content': 'This is the first assistant response.'}, {'role': 'user', 'content': 'This is the second user input.'}, ] print('###### Default (yet Correct) Chat Template ######') print(toker.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)) print('###### Corrected Chat Template ######') chat_template = open('./chat_templates/llama-3-instruct.jinja').read() chat_template = chat_template.replace(' ', '').replace('\n', '') toker.chat_template = chat_template print(toker.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)) ``` Expected output: ``` ###### Default (yet Correct) Chat Template ###### <|begin_of_text|><|start_header_id|>system<|end_header_id|> This is a system prompt.<|eot_id|><|start_header_id|>user<|end_header_id|> This is the first user input.<|eot_id|><|start_header_id|>assistant<|end_header_id|> This is the first assistant response.<|eot_id|><|start_header_id|>user<|end_header_id|> This is the second user input.<|eot_id|><|start_header_id|>assistant<|end_header_id|> ###### Corrected Chat Template ###### <|begin_of_text|><|start_header_id|>system<|end_header_id|> This is a system prompt.<|eot_id|><|start_header_id|>user<|end_header_id|> This is the first user input.<|eot_id|><|start_header_id|>assistant<|end_header_id|> This is the first assistant response.<|eot_id|><|start_header_id|>user<|end_header_id|> This is the second user input.<|eot_id|><|start_header_id|>assistant<|end_header_id|> ```Example 2: Mistral-7B-Instruct-v0.2
For `mistral-instruct` (also `gemma-it`), it does not natively support the `system` message, so passing the `system` message would raise error. ```python from transformers import AutoTokenizer toker = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2") messages = [ {'role': 'system', 'content': 'This is a system prompt.'}, {'role': 'user', 'content': 'This is the first user input.'}, {'role': 'assistant', 'content': 'This is the first assistant response.'}, {'role': 'user', 'content': 'This is the second user input.'}, ] print('###### Default (but Improper) Chat Template ######') # raising error #print(toker.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)) print('###### Corrected Chat Template ######') chat_template = open('./chat_templates/mistral-instruct.jinja').read() chat_template = chat_template.replace(' ', '').replace('\n', '') toker.chat_template = chat_template print(toker.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)) ``` Expected output: ``` ###### Default (but Error-Raising) Chat Template ###### jinja2.exceptions.TemplateError: Conversation roles must alternate user/assistant/user/assistant/... ###### Corrected Chat Template ######Example 3: vicuna-7b-v1.5
**NOTE:** In [fast-chat](https://github.com/lm-sys/FastChat/blob/d578599c69d060e6d40943f1b5b72af98956092a/fastchat/conversation.py#L287C3-L287C3), `vicuna` does not add linebreaks between roles' messages. But I found that adding linebreaks leads to a bit better performance (especially for the v1.5 version). Also, I found `vicuna-7/13/33b-v1.3` may not work well when given a system message different from its default one. So I would recommend to use `vicuna-7/13b-v1.5` instead. ```python from transformers import AutoTokenizer toker = AutoTokenizer.from_pretrained("lmsys/vicuna-7b-v1.5") messages = [ {'role': 'system', 'content': 'This is a system prompt.'}, {'role': 'user', 'content': 'This is the first user input.'}, {'role': 'assistant', 'content': 'This is the first assistant response.'}, {'role': 'user', 'content': 'This is the second user input.'}, ] print('###### Default (but Improper) Chat Template ######') print(toker.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)) print('###### Corrected Chat Template ######') chat_template = open('./chat_templates/vicuna.jinja').read() chat_template = chat_template.replace(' ', '').replace('\n', '') toker.chat_template = chat_template print(toker.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)) ``` Expected output: ``` ###### Default (but Improper) Chat Template ######Supported Models
NOTE: The listed models are not inclusive and also include other-sized ones in the same model family