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

Merge branch 'master' into r1-toolcall

Browse source
This commit is contained in:
Olivier Chafik 2025-02-04 15:56:25 +00:00
commit 933f7a186e
11 changed files with 149 additions and 49 deletions
Download patch file Download diff file Expand all files Collapse all files

7
examples/server/tests/unit/test_tool_call.py
View file

@ -275,7 +275,8 @@ def test_completion_without_tool_call_slow(template_name: str, n_predict: int, t
@pytest.mark.slow
@pytest.mark.parametrize("hf_repo,template_override", [
("bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M", None),
("bartowski/c4ai-command-r7b-12-2024-GGUF:Q4_K_M", ("CohereForAI/c4ai-command-r7b-12-2024", "tool_use")),
("bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", None),
("bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", "chatml"),
@ -299,13 +300,15 @@ def test_completion_without_tool_call_slow(template_name: str, n_predict: int, t
("bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M", ("meta-llama/Llama-3.2-3B-Instruct", None)),
("bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M", "chatml"),
("bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M", None),
# Note: gemma-2-2b-it knows itself as "model", not "assistant", so we don't test the ill-suited chatml on it.
("bartowski/gemma-2-2b-it-GGUF:Q4_K_M", None),
# ("bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M", ("meta-llama/Llama-3.2-3B-Instruct", None)),
])
def test_weather_tool_call(hf_repo: str, template_override: str | Tuple[str, str | None] | None):
def test_weather(hf_repo: str, template_override: Tuple[str, str | None] | None):
global server
n_predict = 512
server.n_slots = 1