Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -48,8 +48,10 @@ model-index:
|
|
| 48 |
type: visual-question-answering
|
| 49 |
name: Visual Reasoning
|
| 50 |
dataset:
|
| 51 |
-
name: FinRAGBench
|
| 52 |
type: FinRAGBench/FinRAGBench-V
|
|
|
|
|
|
|
| 53 |
metrics:
|
| 54 |
- type: accuracy
|
| 55 |
value: 91.2
|
|
@@ -58,8 +60,10 @@ model-index:
|
|
| 58 |
type: text-classification
|
| 59 |
name: Anti-Hallucination
|
| 60 |
dataset:
|
| 61 |
-
name:
|
| 62 |
type: THUDM/RGB
|
|
|
|
|
|
|
| 63 |
metrics:
|
| 64 |
- type: accuracy
|
| 65 |
value: 94.0
|
|
@@ -68,8 +72,10 @@ model-index:
|
|
| 68 |
type: tabular-classification
|
| 69 |
name: End-to-End Latency
|
| 70 |
dataset:
|
| 71 |
-
name:
|
| 72 |
type: FastMemory/Scale
|
|
|
|
|
|
|
| 73 |
metrics:
|
| 74 |
- type: accuracy
|
| 75 |
value: 99.9
|
|
@@ -78,8 +84,10 @@ model-index:
|
|
| 78 |
type: text-retrieval
|
| 79 |
name: Multi-hop Routing
|
| 80 |
dataset:
|
| 81 |
-
name: GraphRAG-Bench
|
| 82 |
type: GraphRAG-Bench/GraphRAG-Bench
|
|
|
|
|
|
|
| 83 |
metrics:
|
| 84 |
- type: accuracy
|
| 85 |
value: 98.0
|
|
@@ -88,8 +96,10 @@ model-index:
|
|
| 88 |
type: text-retrieval
|
| 89 |
name: E-Commerce Graph
|
| 90 |
dataset:
|
| 91 |
-
name:
|
| 92 |
type: snap-stanford/stark
|
|
|
|
|
|
|
| 93 |
metrics:
|
| 94 |
- type: accuracy
|
| 95 |
value: 100.0
|
|
@@ -98,8 +108,10 @@ model-index:
|
|
| 98 |
type: question-answering
|
| 99 |
name: Biomedical Compliance
|
| 100 |
dataset:
|
| 101 |
-
name:
|
| 102 |
type: kg-rag/BiomixQA
|
|
|
|
|
|
|
| 103 |
metrics:
|
| 104 |
- type: accuracy
|
| 105 |
value: 100.0
|
|
@@ -108,8 +120,10 @@ model-index:
|
|
| 108 |
type: text-generation
|
| 109 |
name: Pipeline Eval (RAGAS)
|
| 110 |
dataset:
|
| 111 |
-
name:
|
| 112 |
type: ragas/ragas-eval
|
|
|
|
|
|
|
| 113 |
metrics:
|
| 114 |
- type: accuracy
|
| 115 |
value: 100.0
|
|
|
|
| 48 |
type: visual-question-answering
|
| 49 |
name: Visual Reasoning
|
| 50 |
dataset:
|
| 51 |
+
name: FinRAGBench-V
|
| 52 |
type: FinRAGBench/FinRAGBench-V
|
| 53 |
+
config: default
|
| 54 |
+
split: test
|
| 55 |
metrics:
|
| 56 |
- type: accuracy
|
| 57 |
value: 91.2
|
|
|
|
| 60 |
type: text-classification
|
| 61 |
name: Anti-Hallucination
|
| 62 |
dataset:
|
| 63 |
+
name: RGB
|
| 64 |
type: THUDM/RGB
|
| 65 |
+
config: default
|
| 66 |
+
split: test
|
| 67 |
metrics:
|
| 68 |
- type: accuracy
|
| 69 |
value: 94.0
|
|
|
|
| 72 |
type: tabular-classification
|
| 73 |
name: End-to-End Latency
|
| 74 |
dataset:
|
| 75 |
+
name: Scale Benchmark
|
| 76 |
type: FastMemory/Scale
|
| 77 |
+
config: default
|
| 78 |
+
split: train
|
| 79 |
metrics:
|
| 80 |
- type: accuracy
|
| 81 |
value: 99.9
|
|
|
|
| 84 |
type: text-retrieval
|
| 85 |
name: Multi-hop Routing
|
| 86 |
dataset:
|
| 87 |
+
name: GraphRAG-Bench
|
| 88 |
type: GraphRAG-Bench/GraphRAG-Bench
|
| 89 |
+
config: default
|
| 90 |
+
split: test
|
| 91 |
metrics:
|
| 92 |
- type: accuracy
|
| 93 |
value: 98.0
|
|
|
|
| 96 |
type: text-retrieval
|
| 97 |
name: E-Commerce Graph
|
| 98 |
dataset:
|
| 99 |
+
name: STaRK-Prime
|
| 100 |
type: snap-stanford/stark
|
| 101 |
+
config: default
|
| 102 |
+
split: test
|
| 103 |
metrics:
|
| 104 |
- type: accuracy
|
| 105 |
value: 100.0
|
|
|
|
| 108 |
type: question-answering
|
| 109 |
name: Biomedical Compliance
|
| 110 |
dataset:
|
| 111 |
+
name: BiomixQA
|
| 112 |
type: kg-rag/BiomixQA
|
| 113 |
+
config: mcq
|
| 114 |
+
split: train
|
| 115 |
metrics:
|
| 116 |
- type: accuracy
|
| 117 |
value: 100.0
|
|
|
|
| 120 |
type: text-generation
|
| 121 |
name: Pipeline Eval (RAGAS)
|
| 122 |
dataset:
|
| 123 |
+
name: Pipeline Eval (RAGAS)
|
| 124 |
type: ragas/ragas-eval
|
| 125 |
+
config: default
|
| 126 |
+
split: train
|
| 127 |
metrics:
|
| 128 |
- type: accuracy
|
| 129 |
value: 100.0
|