mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-27 08:21:30 +00:00
chat : nemotron thinking & toolcalling support (#15676)
* feat: nemotron thinking & toolcalling support * Trailing whitespaces * Corrected template for Nemotron * Template and parser fixes * Final template and grammar changes * Whitespace * Always do lazy grammar processing since </think> tag will always be there. * Allow extra content after toolcall * Whitespace * New tests: thinking + tools, tools + content, thinking + tools + content (new!) * Whitespace * Remove cURL test script
This commit is contained in:
committed by
GitHub
parent
9e2b1e83c6
commit
b2426e469e
@@ -112,6 +112,7 @@ enum common_chat_format {
|
||||
COMMON_CHAT_FORMAT_GRANITE,
|
||||
COMMON_CHAT_FORMAT_GPT_OSS,
|
||||
COMMON_CHAT_FORMAT_SEED_OSS,
|
||||
COMMON_CHAT_FORMAT_NEMOTRON_V2,
|
||||
|
||||
COMMON_CHAT_FORMAT_COUNT, // Not a format, just the # formats
|
||||
};
|
||||
|
||||
Reference in New Issue
Block a user