Update README.md
Browse files
README.md
CHANGED
|
@@ -29,7 +29,7 @@ model-index:
|
|
| 29 |
metrics:
|
| 30 |
- name: f1 Score
|
| 31 |
type: f1 Score
|
| 32 |
-
value:
|
| 33 |
- task:
|
| 34 |
type: Summarization
|
| 35 |
dataset:
|
|
@@ -38,7 +38,7 @@ model-index:
|
|
| 38 |
metrics:
|
| 39 |
- name: Faithfullness (facebook/bart-large-cnn)
|
| 40 |
type: facebook/bart-large-cnn
|
| 41 |
-
value:
|
| 42 |
- task:
|
| 43 |
type: Summarization
|
| 44 |
dataset:
|
|
@@ -47,7 +47,7 @@ model-index:
|
|
| 47 |
metrics:
|
| 48 |
- name: Summarization Compression
|
| 49 |
type: Lighteval extractiveness
|
| 50 |
-
value:
|
| 51 |
- task:
|
| 52 |
type: Summarization
|
| 53 |
dataset:
|
|
@@ -56,7 +56,7 @@ model-index:
|
|
| 56 |
metrics:
|
| 57 |
- name: Summarization Coverage
|
| 58 |
type: Lighteval extractiveness
|
| 59 |
-
value:
|
| 60 |
- task:
|
| 61 |
type: Summarization
|
| 62 |
dataset:
|
|
@@ -65,7 +65,7 @@ model-index:
|
|
| 65 |
metrics:
|
| 66 |
- name: Summarization Density
|
| 67 |
type: Lighteval extractiveness
|
| 68 |
-
value:
|
| 69 |
- task:
|
| 70 |
type: Summarization
|
| 71 |
dataset:
|
|
@@ -74,7 +74,7 @@ model-index:
|
|
| 74 |
metrics:
|
| 75 |
- name: rougeL precision
|
| 76 |
type: Lighteval
|
| 77 |
-
value:
|
| 78 |
- task:
|
| 79 |
type: Summarization
|
| 80 |
dataset:
|
|
@@ -83,7 +83,7 @@ model-index:
|
|
| 83 |
metrics:
|
| 84 |
- name: rougeL recall
|
| 85 |
type: Lighteval
|
| 86 |
-
value:
|
| 87 |
- task:
|
| 88 |
type: Summarization
|
| 89 |
dataset:
|
|
@@ -92,7 +92,7 @@ model-index:
|
|
| 92 |
metrics:
|
| 93 |
- name: rougeL fmeasure
|
| 94 |
type: Lighteval
|
| 95 |
-
value:
|
| 96 |
- task:
|
| 97 |
type: Summarization
|
| 98 |
dataset:
|
|
@@ -101,7 +101,7 @@ model-index:
|
|
| 101 |
metrics:
|
| 102 |
- name: rouge1 precision
|
| 103 |
type: Lighteval
|
| 104 |
-
value:
|
| 105 |
- task:
|
| 106 |
type: Summarization
|
| 107 |
dataset:
|
|
@@ -110,7 +110,7 @@ model-index:
|
|
| 110 |
metrics:
|
| 111 |
- name: rouge1 recall
|
| 112 |
type: Lighteval
|
| 113 |
-
value:
|
| 114 |
- task:
|
| 115 |
type: Summarization
|
| 116 |
dataset:
|
|
@@ -119,7 +119,7 @@ model-index:
|
|
| 119 |
metrics:
|
| 120 |
- name: rouge1 fmeasure
|
| 121 |
type: Lighteval
|
| 122 |
-
value:
|
| 123 |
---
|
| 124 |
|
| 125 |
# This model was built to shorten text that is injected into LLM prompts to reduce API calling costs
|
|
|
|
| 29 |
metrics:
|
| 30 |
- name: f1 Score
|
| 31 |
type: f1 Score
|
| 32 |
+
value: 0.29
|
| 33 |
- task:
|
| 34 |
type: Summarization
|
| 35 |
dataset:
|
|
|
|
| 38 |
metrics:
|
| 39 |
- name: Faithfullness (facebook/bart-large-cnn)
|
| 40 |
type: facebook/bart-large-cnn
|
| 41 |
+
value: 1.71
|
| 42 |
- task:
|
| 43 |
type: Summarization
|
| 44 |
dataset:
|
|
|
|
| 47 |
metrics:
|
| 48 |
- name: Summarization Compression
|
| 49 |
type: Lighteval extractiveness
|
| 50 |
+
value: 7.52
|
| 51 |
- task:
|
| 52 |
type: Summarization
|
| 53 |
dataset:
|
|
|
|
| 56 |
metrics:
|
| 57 |
- name: Summarization Coverage
|
| 58 |
type: Lighteval extractiveness
|
| 59 |
+
value: 0.96
|
| 60 |
- task:
|
| 61 |
type: Summarization
|
| 62 |
dataset:
|
|
|
|
| 65 |
metrics:
|
| 66 |
- name: Summarization Density
|
| 67 |
type: Lighteval extractiveness
|
| 68 |
+
value: 8.68
|
| 69 |
- task:
|
| 70 |
type: Summarization
|
| 71 |
dataset:
|
|
|
|
| 74 |
metrics:
|
| 75 |
- name: rougeL precision
|
| 76 |
type: Lighteval
|
| 77 |
+
value: 0.59
|
| 78 |
- task:
|
| 79 |
type: Summarization
|
| 80 |
dataset:
|
|
|
|
| 83 |
metrics:
|
| 84 |
- name: rougeL recall
|
| 85 |
type: Lighteval
|
| 86 |
+
value: 0.31
|
| 87 |
- task:
|
| 88 |
type: Summarization
|
| 89 |
dataset:
|
|
|
|
| 92 |
metrics:
|
| 93 |
- name: rougeL fmeasure
|
| 94 |
type: Lighteval
|
| 95 |
+
value: 0.41
|
| 96 |
- task:
|
| 97 |
type: Summarization
|
| 98 |
dataset:
|
|
|
|
| 101 |
metrics:
|
| 102 |
- name: rouge1 precision
|
| 103 |
type: Lighteval
|
| 104 |
+
value: 0.63
|
| 105 |
- task:
|
| 106 |
type: Summarization
|
| 107 |
dataset:
|
|
|
|
| 110 |
metrics:
|
| 111 |
- name: rouge1 recall
|
| 112 |
type: Lighteval
|
| 113 |
+
value: 0.33
|
| 114 |
- task:
|
| 115 |
type: Summarization
|
| 116 |
dataset:
|
|
|
|
| 119 |
metrics:
|
| 120 |
- name: rouge1 fmeasure
|
| 121 |
type: Lighteval
|
| 122 |
+
value: 0.44
|
| 123 |
---
|
| 124 |
|
| 125 |
# This model was built to shorten text that is injected into LLM prompts to reduce API calling costs
|