Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
Commit
·
606d718
1
Parent(s):
77ded94
Modify the evaluation steps
Browse files- src/about.py +7 -14
src/about.py
CHANGED
|
@@ -19,20 +19,15 @@ EVALUATION_QUEUE_TEXT = """
|
|
| 19 |
|
| 20 |
1. Install AIR-Bench
|
| 21 |
```bash
|
| 22 |
-
|
| 23 |
-
git clone https://github.com/AIR-Bench/AIR-Bench.git
|
| 24 |
-
|
| 25 |
-
# Install the package
|
| 26 |
-
cd AIR-Bench
|
| 27 |
-
pip install .
|
| 28 |
```
|
| 29 |
2. Run the evaluation script
|
| 30 |
```bash
|
| 31 |
cd AIR-Bench/scripts
|
| 32 |
# Run all tasks
|
| 33 |
-
python
|
| 34 |
--output_dir ./search_results \\
|
| 35 |
-
--encoder BAAI/bge-m3
|
| 36 |
--reranker BAAI/bge-reranker-v2-m3 \\
|
| 37 |
--search_top_k 1000 \\
|
| 38 |
--rerank_top_k 100 \\
|
|
@@ -46,7 +41,7 @@ python run_AIR-Bench.py \\
|
|
| 46 |
--overwrite False
|
| 47 |
|
| 48 |
# Run the tasks in the specified task type
|
| 49 |
-
python
|
| 50 |
--task_types long-doc \\
|
| 51 |
--output_dir ./search_results \\
|
| 52 |
--encoder BAAI/bge-m3 \\
|
|
@@ -63,7 +58,7 @@ python run_AIR-Bench.py \\
|
|
| 63 |
--overwrite False
|
| 64 |
|
| 65 |
# Run the tasks in the specified task type and domains
|
| 66 |
-
python
|
| 67 |
--task_types long-doc \\
|
| 68 |
--domains arxiv book \\
|
| 69 |
--output_dir ./search_results \\
|
|
@@ -81,7 +76,7 @@ python run_AIR-Bench.py \\
|
|
| 81 |
--overwrite False
|
| 82 |
|
| 83 |
# Run the tasks in the specified languages
|
| 84 |
-
python
|
| 85 |
--languages en \\
|
| 86 |
--output_dir ./search_results \\
|
| 87 |
--encoder BAAI/bge-m3 \\
|
|
@@ -98,15 +93,13 @@ python run_AIR-Bench.py \\
|
|
| 98 |
--overwrite False
|
| 99 |
|
| 100 |
# Run the tasks in the specified task type, domains, and languages
|
| 101 |
-
python
|
| 102 |
--task_types qa \\
|
| 103 |
--domains wiki web \\
|
| 104 |
--languages en \\
|
| 105 |
--output_dir ./search_results \\
|
| 106 |
--encoder BAAI/bge-m3 \\
|
| 107 |
-
--encoder_link https://huggingface.co/BAAI/bge-m3 \\
|
| 108 |
--reranker BAAI/bge-reranker-v2-m3 \\
|
| 109 |
-
--reranker_link https://huggingface.co/BAAI/bge-reranker-v2-m3 \\
|
| 110 |
--search_top_k 1000 \\
|
| 111 |
--rerank_top_k 100 \\
|
| 112 |
--max_query_length 512 \\
|
|
|
|
| 19 |
|
| 20 |
1. Install AIR-Bench
|
| 21 |
```bash
|
| 22 |
+
pip install air-benchmark
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
```
|
| 24 |
2. Run the evaluation script
|
| 25 |
```bash
|
| 26 |
cd AIR-Bench/scripts
|
| 27 |
# Run all tasks
|
| 28 |
+
python run_air_benchmark.py \\
|
| 29 |
--output_dir ./search_results \\
|
| 30 |
+
--encoder BAAI/bge-m3 \\
|
| 31 |
--reranker BAAI/bge-reranker-v2-m3 \\
|
| 32 |
--search_top_k 1000 \\
|
| 33 |
--rerank_top_k 100 \\
|
|
|
|
| 41 |
--overwrite False
|
| 42 |
|
| 43 |
# Run the tasks in the specified task type
|
| 44 |
+
python run_air_benchmark.py \\
|
| 45 |
--task_types long-doc \\
|
| 46 |
--output_dir ./search_results \\
|
| 47 |
--encoder BAAI/bge-m3 \\
|
|
|
|
| 58 |
--overwrite False
|
| 59 |
|
| 60 |
# Run the tasks in the specified task type and domains
|
| 61 |
+
python run_air_benchmark.py \\
|
| 62 |
--task_types long-doc \\
|
| 63 |
--domains arxiv book \\
|
| 64 |
--output_dir ./search_results \\
|
|
|
|
| 76 |
--overwrite False
|
| 77 |
|
| 78 |
# Run the tasks in the specified languages
|
| 79 |
+
python run_air_benchmark.py \\
|
| 80 |
--languages en \\
|
| 81 |
--output_dir ./search_results \\
|
| 82 |
--encoder BAAI/bge-m3 \\
|
|
|
|
| 93 |
--overwrite False
|
| 94 |
|
| 95 |
# Run the tasks in the specified task type, domains, and languages
|
| 96 |
+
python run_air_benchmark.py \\
|
| 97 |
--task_types qa \\
|
| 98 |
--domains wiki web \\
|
| 99 |
--languages en \\
|
| 100 |
--output_dir ./search_results \\
|
| 101 |
--encoder BAAI/bge-m3 \\
|
|
|
|
| 102 |
--reranker BAAI/bge-reranker-v2-m3 \\
|
|
|
|
| 103 |
--search_top_k 1000 \\
|
| 104 |
--rerank_top_k 100 \\
|
| 105 |
--max_query_length 512 \\
|