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

tool-call: command r7b fix for normal responses (#11608)

Browse source 
* fix command r7b normal response regex + add to server test

* test multiline non-tool-call responses in test-chat
This commit is contained in:
Olivier Chafik 2025-02-04 15:48:53 +00:00 • committed by GitHub
parent 106045e7bb
commit db288b60cb
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 19 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

8
examples/server/tests/unit/test_tool_call.py
View file

@ -273,6 +273,7 @@ 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/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"),
@ -303,12 +304,13 @@ def test_completion_without_tool_call_slow(template_name: str, n_predict: int, t
# ("bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M", ("meta-llama/Llama-3.2-3B-Instruct", None)),
# ("bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M", 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
server.jinja = True
server.n_ctx = 8192
server.n_predict = 512
server.n_predict = n_predict
server.model_hf_repo = hf_repo
server.model_hf_file = None
if isinstance(template_override, tuple):
@ -319,7 +321,7 @@ def test_weather_tool_call(hf_repo: str, template_override: str | Tuple[str, str
server.chat_template = template_override
server.start(timeout_seconds=TIMEOUT_SERVER_START)
res = server.make_request("POST", "/chat/completions", data={
"max_tokens": 256,
"max_tokens": n_predict,
"messages": [
{"role": "user", "content": "What is the weather in Istanbul?"},
],