|
9 | 9 |
|
10 | 10 | cmake -B build -DLLAMA_CURL=1 && cmake --build build --config Release -j -t llama-server |
11 | 11 |
|
| 12 | + export LLAMA_SERVER_BIN_PATH=$PWD/build/bin/llama-server |
| 13 | + export LLAMA_CACHE=${LLAMA_CACHE:-$HOME/Library/Caches/llama.cpp} |
| 14 | +
|
12 | 15 | ./scripts/tool_bench.py run --n 30 --temp -1 --temp 0 --temp 1 --model "Qwen 2.5 1.5B Q4_K_M" --output qwen1.5b.jsonl --hf bartowski/Qwen2.5-1.5B-Instruct-GGUF --ollama qwen2.5:1.5b-instruct-q4_K_M |
13 | 16 | ./scripts/tool_bench.py run --n 30 --temp -1 --temp 0 --temp 1 --model "Qwen 2.5 Coder 7B Q4_K_M" --output qwenc7b.jsonl --hf bartowski/Qwen2.5-Coder-7B-Instruct-GGUF --ollama qwen2.5-coder:7b |
14 | 17 |
|
|
48 | 51 |
|
49 | 52 | sys.path.insert(0, Path(__file__).parent.parent.as_posix()) |
50 | 53 | if True: |
51 | | - from examples.server.tests.utils import ServerProcess # type: ignore |
52 | | - from examples.server.tests.unit.test_tool_call import TIMEOUT_SERVER_START, do_test_calc_result, do_test_hello_world, do_test_weather # type: ignore |
| 54 | + from examples.server.tests.utils import ServerProcess |
| 55 | + from examples.server.tests.unit.test_tool_call import TIMEOUT_SERVER_START, do_test_calc_result, do_test_hello_world, do_test_weather |
53 | 56 |
|
54 | 57 |
|
55 | 58 | @contextmanager |
@@ -169,9 +172,9 @@ def plot(files: List[Path], output: Optional[Path] = None, test_regex: Optional[ |
169 | 172 | ] |
170 | 173 | matrix.append(row_vals) |
171 | 174 |
|
172 | | - columns = [f"{server_name}\n{test}" for server_name, test in all_cols] |
| 175 | + columns: list[str] = [f"{server_name}\n{test}" for server_name, test in all_cols] |
173 | 176 |
|
174 | | - df = pd.DataFrame(matrix, index=index, columns=columns) |
| 177 | + df = pd.DataFrame(matrix, index=np.array(index), columns=np.array(columns)) |
175 | 178 |
|
176 | 179 | plt.figure(figsize=(12, 6)) |
177 | 180 |
|
|
0 commit comments