riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-03 12:50:06 +06:00
Code Issues Actions 28 Packages Projects Releases Wiki Activity

Update chat_extras.md with content correction (#36599)

Browse Source 
Update chat_extras.md - content

Fixed a typo in the content, that may confuse the readers.
This commit is contained in:
Krishnakumar Kannan 2025-03-07 06:09:02 -07:00 committed by GitHub
parent f2e197c30a
commit 1b9978c360
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/en/chat_extras.md
View File

@ -146,7 +146,7 @@ print(tokenizer.decode(out[0][len(inputs["input_ids"][0]):]))
## Schema
[`~PreTrainedTokenizerBase.apply_chat_template`] converts functions into a [JSON schema](https://json-schema.org/learn/getting-started-step-by-step) which is passed to the chat template. A LLM never sees the code inside the function. In other words, a LLM doesn't care how the model works technically, it only cares about function **definition** and **arguments**.
[`~PreTrainedTokenizerBase.apply_chat_template`] converts functions into a [JSON schema](https://json-schema.org/learn/getting-started-step-by-step) which is passed to the chat template. A LLM never sees the code inside the function. In other words, a LLM doesn't care how the function works technically, it only cares about function **definition** and **arguments**.
The JSON schema is automatically generated behind the scenes as long as your function follows the [rules](#tools) listed earlier above. But you can use [get_json_schema](https://github.com/huggingface/transformers/blob/14561209291255e51c55260306c7d00c159381a5/src/transformers/utils/chat_template_utils.py#L205) to manually convert a schema for more visibility or debugging.