Upload README.md with huggingface_hub

README.md

@@ -12,7 +12,7 @@ model-index:
       type: question-answering
       name: Financial Q&A
     dataset:
-      name: Finance Bench
+      name: "[FinanceBench](https://huggingface.co/datasets/PatronusAI/financebench)"
       type: PatronusAI/financebench
       config: financebench
       split: train
@@ -24,7 +24,7 @@ model-index:
       type: text2text-generation
       name: Table Preservation
     dataset:
-      name: T2-RAGBench
+      name: "[T2-RAGBench](https://huggingface.co/datasets/G4KMU/t2-ragbench)"
       type: G4KMU/t2-ragbench
       config: default
       split: test
@@ -36,7 +36,7 @@ model-index:
       type: text-retrieval
       name: Multi-Doc Synthesis
     dataset:
-      name: FRAMES
+      name: "[FRAMES](https://huggingface.co/datasets/google/frames-benchmark)"
       type: google/frames-benchmark
       config: default
       split: test
@@ -48,7 +48,7 @@ model-index:
       type: visual-question-answering
       name: Visual Reasoning
     dataset:
-      name: FinRAGBench-V
+      name: "[FinRAGBench-V](https://huggingface.co/datasets/FinRAGBench/FinRAGBench-V)"
       type: FinRAGBench/FinRAGBench-V
       config: default
       split: test
@@ -60,7 +60,7 @@ model-index:
       type: text-classification
       name: Anti-Hallucination
     dataset:
-      name: RGB
+      name: "[RGB](https://huggingface.co/datasets/THUDM/RGB)"
       type: THUDM/RGB
       config: default
       split: test
@@ -72,7 +72,7 @@ model-index:
       type: tabular-classification
       name: End-to-End Latency
     dataset:
-      name: Scale Benchmark
+      name: "[Scale Benchmark](https://github.com/fastbuilderai/scale)"
       type: FastMemory/Scale
       config: default
       split: train
@@ -84,7 +84,7 @@ model-index:
       type: text-retrieval
       name: Multi-hop Routing
     dataset:
-      name: GraphRAG-Bench
+      name: "[GraphRAG-Bench](https://huggingface.co/datasets/GraphRAG-Bench/GraphRAG-Bench)"
       type: GraphRAG-Bench/GraphRAG-Bench
       config: default
       split: test
@@ -96,7 +96,7 @@ model-index:
       type: text-retrieval
       name: E-Commerce Graph
     dataset:
-      name: STaRK-Prime
+      name: "[STaRK-Prime](https://huggingface.co/datasets/snap-stanford/stark)"
       type: snap-stanford/stark
       config: default
       split: test
@@ -108,7 +108,7 @@ model-index:
       type: question-answering
       name: Biomedical Compliance
     dataset:
-      name: BiomixQA
+      name: "[BiomixQA](https://huggingface.co/datasets/kg-rag/BiomixQA)"
       type: kg-rag/BiomixQA
       config: mcq
       split: train
@@ -120,7 +120,7 @@ model-index:
       type: text-generation
       name: Pipeline Eval (RAGAS)
     dataset:
-      name: Pipeline Eval (RAGAS)
+      name: "[Pipeline Eval (RAGAS)](https://huggingface.co/datasets/ragas/ragas-eval)"
       type: ragas/ragas-eval
       config: default
       split: train