Update README.md
Browse files
README.md
CHANGED
|
@@ -557,8 +557,6 @@ model-index:
|
|
| 557 |
- type: recall_at_5
|
| 558 |
value: 85.9
|
| 559 |
---
|
| 560 |
-
license: apache-2.0
|
| 561 |
-
---
|
| 562 |
|
| 563 |
# Model Introduction
|
| 564 |
360Zhinao-search uses the self-developed BERT model as the base for multi-task fine-tuning, which has an average score of 75.05 on the Retrieval task on the C-MTEB-Retrieval benchmark, currently ranking first.
|
|
@@ -579,7 +577,6 @@ license: apache-2.0
|
|
| 579 |
3. Negative example mining: Use multiple methods to deeply mine difficult-to-distinguish negative examples to improve information gain;
|
| 580 |
4. Training efficiency: multi-machine multi-CPU + Deepspeed method to optimize GPU memory utilization.
|
| 581 |
|
| 582 |
-
|
| 583 |
## Usage
|
| 584 |
```bash
|
| 585 |
from typing import cast, List, Dict, Union
|
|
|
|
| 557 |
- type: recall_at_5
|
| 558 |
value: 85.9
|
| 559 |
---
|
|
|
|
|
|
|
| 560 |
|
| 561 |
# Model Introduction
|
| 562 |
360Zhinao-search uses the self-developed BERT model as the base for multi-task fine-tuning, which has an average score of 75.05 on the Retrieval task on the C-MTEB-Retrieval benchmark, currently ranking first.
|
|
|
|
| 577 |
3. Negative example mining: Use multiple methods to deeply mine difficult-to-distinguish negative examples to improve information gain;
|
| 578 |
4. Training efficiency: multi-machine multi-CPU + Deepspeed method to optimize GPU memory utilization.
|
| 579 |
|
|
|
|
| 580 |
## Usage
|
| 581 |
```bash
|
| 582 |
from typing import cast, List, Dict, Union
|