Better table labels

README.md

@@ -5,7 +5,7 @@ tags:
 - reranker
 - qwen2_vl
 ---
-# MonoQwen2-VL-2B-LoRA-Reranker
+# MonoQwen2-VL-v0.1
 
 ## Model Overview
 The **MonoQwen2-VL-v0.1** is a LoRA of the Qwen2-VL-2B model, optimized for reranking (i.e, asserting pointwise image-query relevance) using the [MonoT5](https://arxiv.org/pdf/2101.05667) objective.
@@ -79,7 +79,7 @@ This example demonstrates how to use the model to assess the relevance of an ima
 
 The model has been evaluated on [ViDoRe Benchmark](https://huggingface.co/spaces/vidore/vidore-leaderboard), by retrieving 10 elements with [MrLight_dse-qwen2-2b-mrl-v1](https://huggingface.co/MrLight/dse-qwen2-2b-mrl-v1) and reranking them. The table below summarizes its `ndcg@5` scores:
 
-| Dataset                                           | NDCG@5 Before Reranking  | NDCG@5 After Reranking |
+| Dataset                                           | [MrLight_dse-qwen2-2b-mrl-v1](https://huggingface.co/MrLight/dse-qwen2-2b-mrl-v1)  | MonoQwen2-VL-v0.1 reranking |
 |---------------------------------------------------|--------------------------|------------------------|
 | vidore/arxivqa_test_subsampled                    | 85.6                     | 89.0                   |
 | vidore/docvqa_test_subsampled                     | 57.1                     | 59.7                   |