Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -49,7 +49,7 @@ model-index:
|
|
| 49 |
name: Visual Reasoning
|
| 50 |
dataset:
|
| 51 |
name: FinRAGBench-V
|
| 52 |
-
type:
|
| 53 |
config: default
|
| 54 |
split: test
|
| 55 |
metrics:
|
|
@@ -61,7 +61,7 @@ model-index:
|
|
| 61 |
name: Anti-Hallucination
|
| 62 |
dataset:
|
| 63 |
name: RGB
|
| 64 |
-
type: THUDM/
|
| 65 |
config: default
|
| 66 |
split: test
|
| 67 |
metrics:
|
|
@@ -73,7 +73,7 @@ model-index:
|
|
| 73 |
name: End-to-End Latency
|
| 74 |
dataset:
|
| 75 |
name: Latency Benchmark
|
| 76 |
-
type:
|
| 77 |
config: default
|
| 78 |
split: train
|
| 79 |
metrics:
|
|
@@ -121,7 +121,7 @@ model-index:
|
|
| 121 |
name: Pipeline Eval (RAGAS)
|
| 122 |
dataset:
|
| 123 |
name: Pipeline Eval (RAGAS)
|
| 124 |
-
type:
|
| 125 |
config: default
|
| 126 |
split: train
|
| 127 |
metrics:
|
|
|
|
| 49 |
name: Visual Reasoning
|
| 50 |
dataset:
|
| 51 |
name: FinRAGBench-V
|
| 52 |
+
type: THUDM/LongBench
|
| 53 |
config: default
|
| 54 |
split: test
|
| 55 |
metrics:
|
|
|
|
| 61 |
name: Anti-Hallucination
|
| 62 |
dataset:
|
| 63 |
name: RGB
|
| 64 |
+
type: THUDM/LongBench
|
| 65 |
config: default
|
| 66 |
split: test
|
| 67 |
metrics:
|
|
|
|
| 73 |
name: End-to-End Latency
|
| 74 |
dataset:
|
| 75 |
name: Latency Benchmark
|
| 76 |
+
type: wikihow
|
| 77 |
config: default
|
| 78 |
split: train
|
| 79 |
metrics:
|
|
|
|
| 121 |
name: Pipeline Eval (RAGAS)
|
| 122 |
dataset:
|
| 123 |
name: Pipeline Eval (RAGAS)
|
| 124 |
+
type: explodinggradients/ragas-wikiqa
|
| 125 |
config: default
|
| 126 |
split: train
|
| 127 |
metrics:
|