Upload README.md with huggingface_hub

README.md

@@ -70,7 +70,7 @@ We have validated the performance of our model on the [mteb-chinese-reranking le
 
 | Model | T2Reranking | MMarcoReranking | CMedQAv1 | CMedQAv2 | Avg |  
 |:-------------------------------|:--------:|:--------:|:--------:|:--------:|:--------:|  
-| **360Zhinao-1_8B-reranking** | 68.55 | 37.29 | 86.75 | 87.92 | 70.13 |
+| **360Zhinao-1_8B-reranking** | **68.55** | **37.29** | **86.75** | **87.92** | **70.13** |
 | piccolo-large-zh-v2 | 67.15 | 33.39 | 90.14 | 89.31 | 70 |
 | Baichuan-text-embedding | 67.85 | 34.3 | 88.46 | 88.06 | 69.67 |
 | stella-mrl-large-zh-v3.5-1792d | 66.43 | 28.85 | 89.18 | 89.33 | 68.45 |
@@ -115,6 +115,8 @@ Unlike generative tasks that produce multiple characters, using generative model
 
 # Inference Script
 
+You can copy the following scripts to [mteb-eval-scripts](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB), then replace FlagReranker with FlagRerankerCustom in [eval_cross_encoder](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB/eval_cross_encoder.py) scripts, then run [eval_cross_encoder](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB/eval_cross_encoder.py) to reproduce our complete performance on the [mteb-chinese-reranking leaderboard](https://huggingface.co/spaces/mteb/leaderboard).
+
 ```python
 from typing import cast, List, Union, Tuple, Dict, Optional
 
@@ -131,7 +133,6 @@ def preprocess(
     tokenizer: transformers.PreTrainedTokenizer,
     max_len: int = 1024,
     system_message: str = "",
-    #system_message: str = "You are a helpful assistant.",
     device = None,
 ) -> Dict:
     roles = {"user": "<|im_start|>user", "assistant": "<|im_start|>assistant"}