ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

server: inject date_string in llama 3.x template + fix date for firefunction v2 (#12802)

Browse source 
* Inject date_string in llama 3.x + fix for functionary v2

https://github.com/ggml-org/llama.cpp/issues/12729

* move/fix detection of functionary v3.1 before llama 3.x, fix & test their non-tool mode

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* generate more tokens in test_completion_with_required_tool_tiny_fast to avoid truncation

---------

Co-authored-by: ochafik <ochafik@google.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Olivier Chafik 2025-05-15 02:39:51 +01:00 • committed by GitHub
parent e3a9421b78
commit aa48e373f2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 185 additions and 112 deletions
Download patch file Download diff file Expand all files Collapse all files

2
tools/server/tests/unit/test_tool_call.py
View file

@ -109,7 +109,7 @@ def do_test_completion_with_required_tool_tiny(server: ServerProcess, tool: dict
])
def test_completion_with_required_tool_tiny_fast(template_name: str, tool: dict, argument_key: str | None):
global server
n_predict = 512
n_predict = 1024
# server = ServerPreset.stories15m_moe()
server.jinja = True
server.n_predict = n_predict