riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-31 02:02:21 +06:00
Code Issues Actions 23 Packages Projects Releases Wiki Activity

Update chat template warnings/guides (#27634)

Browse Source 
* Update default ChatML template

* Update docs/warnings

* Update docs/source/en/chat_templating.md

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* Slight rework

---------

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
This commit is contained in:
Matt 2023-11-27 18:40:10 +00:00 committed by GitHub
parent ce31508134
commit 74a3cebfa5
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
docs/source/en/chat_templating.md
View File

@ -376,7 +376,10 @@ input formats. Our default template for models that don't have a class-specific
```
If you like this one, here it is in one-liner form, ready to copy into your code. The one-liner also includes
handy support for "generation prompts" - see the next section for more!
handy support for [generation prompts](#what-are-generation-prompts), but note that it doesn't add BOS or EOS tokens!
If your model expects those, they won't be added automatically by `apply_chat_template` - in other words, the
text will be tokenized with `add_special_tokens=False`. This is to avoid potential conflicts between the template and
the `add_special_tokens` logic. If your model expects special tokens, make sure to add them to the template!
```
tokenizer.chat_template = "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"

2
src/transformers/tokenization_utils_base.py
View File

@ -1786,7 +1786,7 @@ class PreTrainedTokenizerBase(SpecialTokensMixin, PushToHubMixin):
"""
logger.warning_once(
"\nNo chat template is defined for this tokenizer - using a default chat template "
"that implements the ChatML format. If the default is not appropriate for "
"that implements the ChatML format (without BOS/EOS tokens!). If the default is not appropriate for "
"your model, please set `tokenizer.chat_template` to an appropriate template. "
"See https://huggingface.co/docs/transformers/main/chat_templating for more information.\n"
)