Update app.py
Browse files
app.py
CHANGED
|
@@ -105,6 +105,24 @@ with tab1:
|
|
| 105 |
|
| 106 |
st.markdown('## Metric Explanation')
|
| 107 |
st.markdown('@Farima populate here')
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 108 |
|
| 109 |
# Dropdown menu to filter tiers
|
| 110 |
tiers = ['All Tiers', 'Tier 1: Hard', 'Tier 2: Moderate', 'Tier 3: Easy']
|
|
|
|
| 105 |
|
| 106 |
st.markdown('## Metric Explanation')
|
| 107 |
st.markdown('@Farima populate here')
|
| 108 |
+
st.markdown('''
|
| 109 |
+
- Tier
|
| 110 |
+
- Rank
|
| 111 |
+
- Model
|
| 112 |
+
- Factuality Score
|
| 113 |
+
- Factual Recall
|
| 114 |
+
- Conceptual Understanding
|
| 115 |
+
- Procedural Execution
|
| 116 |
+
- Comparative Analysis
|
| 117 |
+
- Recommendations and Insights
|
| 118 |
+
- Domain-Specific Knowledge
|
| 119 |
+
- Temporal Context
|
| 120 |
+
- Hallucination Score
|
| 121 |
+
- # Tokens
|
| 122 |
+
- # Factual
|
| 123 |
+
- # Undecidable
|
| 124 |
+
- # Unsupported
|
| 125 |
+
''')
|
| 126 |
|
| 127 |
# Dropdown menu to filter tiers
|
| 128 |
tiers = ['All Tiers', 'Tier 1: Hard', 'Tier 2: Moderate', 'Tier 3: Easy']
|