Update README.md
Browse files
README.md
CHANGED
|
@@ -28,16 +28,16 @@ model-index:
|
|
| 28 |
metrics:
|
| 29 |
- name: f1 Score
|
| 30 |
type: f1 Score
|
| 31 |
-
value: 0.
|
| 32 |
- task:
|
| 33 |
type: Summarization
|
| 34 |
dataset:
|
| 35 |
name: shorecode/summary-collection-60k-rows
|
| 36 |
type: shorecode/summary-collection-60k-rows
|
| 37 |
metrics:
|
| 38 |
-
- name: Faithfullness
|
| 39 |
type: facebook/bart-large-cnn
|
| 40 |
-
value: 2.
|
| 41 |
- task:
|
| 42 |
type: Summarization
|
| 43 |
dataset:
|
|
@@ -73,7 +73,7 @@ model-index:
|
|
| 73 |
metrics:
|
| 74 |
- name: rougeL precision
|
| 75 |
type: Lighteval
|
| 76 |
-
value: 0.
|
| 77 |
- task:
|
| 78 |
type: Summarization
|
| 79 |
dataset:
|
|
@@ -82,7 +82,7 @@ model-index:
|
|
| 82 |
metrics:
|
| 83 |
- name: rougeL recall
|
| 84 |
type: Lighteval
|
| 85 |
-
value: 0.
|
| 86 |
- task:
|
| 87 |
type: Summarization
|
| 88 |
dataset:
|
|
@@ -91,7 +91,7 @@ model-index:
|
|
| 91 |
metrics:
|
| 92 |
- name: rougeL fmeasure
|
| 93 |
type: Lighteval
|
| 94 |
-
value: 0.
|
| 95 |
---
|
| 96 |
|
| 97 |
# This model was built to shorten text to be injected into LLM prompts to reduce API calling costs
|
|
|
|
| 28 |
metrics:
|
| 29 |
- name: f1 Score
|
| 30 |
type: f1 Score
|
| 31 |
+
value: 0.308
|
| 32 |
- task:
|
| 33 |
type: Summarization
|
| 34 |
dataset:
|
| 35 |
name: shorecode/summary-collection-60k-rows
|
| 36 |
type: shorecode/summary-collection-60k-rows
|
| 37 |
metrics:
|
| 38 |
+
- name: Faithfullness (facebook/bart-large-cnn)
|
| 39 |
type: facebook/bart-large-cnn
|
| 40 |
+
value: 2.91
|
| 41 |
- task:
|
| 42 |
type: Summarization
|
| 43 |
dataset:
|
|
|
|
| 73 |
metrics:
|
| 74 |
- name: rougeL precision
|
| 75 |
type: Lighteval
|
| 76 |
+
value: 0.56
|
| 77 |
- task:
|
| 78 |
type: Summarization
|
| 79 |
dataset:
|
|
|
|
| 82 |
metrics:
|
| 83 |
- name: rougeL recall
|
| 84 |
type: Lighteval
|
| 85 |
+
value: 0.12
|
| 86 |
- task:
|
| 87 |
type: Summarization
|
| 88 |
dataset:
|
|
|
|
| 91 |
metrics:
|
| 92 |
- name: rougeL fmeasure
|
| 93 |
type: Lighteval
|
| 94 |
+
value: 0.19
|
| 95 |
---
|
| 96 |
|
| 97 |
# This model was built to shorten text to be injected into LLM prompts to reduce API calling costs
|