Update README.md
Browse files
README.md
CHANGED
@@ -65,13 +65,12 @@ model-index:
|
|
65 |
name: Average
|
66 |
type: Aggregated Metrics
|
67 |
metrics:
|
68 |
-
-
|
|
|
69 |
value: 19.46
|
70 |
-
name: Average Score
|
71 |
source:
|
72 |
name: Open LLM Leaderboard
|
73 |
-
url:
|
74 |
-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=P0x0/Astra-v1-12B
|
75 |
|
76 |
- task:
|
77 |
type: text-generation
|
@@ -82,13 +81,15 @@ model-index:
|
|
82 |
args:
|
83 |
num_few_shot: 0
|
84 |
metrics:
|
85 |
-
-
|
|
|
|
|
|
|
|
|
86 |
value: 28.06
|
87 |
-
name: Strict Accuracy
|
88 |
source:
|
89 |
name: Open LLM Leaderboard
|
90 |
-
url:
|
91 |
-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=P0x0/Astra-v1-12B
|
92 |
|
93 |
- task:
|
94 |
type: text-generation
|
@@ -99,13 +100,12 @@ model-index:
|
|
99 |
args:
|
100 |
num_few_shot: 3
|
101 |
metrics:
|
102 |
-
-
|
|
|
103 |
value: 31.81
|
104 |
-
name: Normalized Accuracy
|
105 |
source:
|
106 |
name: Open LLM Leaderboard
|
107 |
-
url:
|
108 |
-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=P0x0/Astra-v1-12B
|
109 |
|
110 |
- task:
|
111 |
type: text-generation
|
@@ -116,13 +116,12 @@ model-index:
|
|
116 |
args:
|
117 |
num_few_shot: 4
|
118 |
metrics:
|
119 |
-
-
|
|
|
120 |
value: 9.67
|
121 |
-
name: Exact Match
|
122 |
source:
|
123 |
name: Open LLM Leaderboard
|
124 |
-
url:
|
125 |
-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=P0x0/Astra-v1-12B
|
126 |
|
127 |
- task:
|
128 |
type: text-generation
|
@@ -133,13 +132,12 @@ model-index:
|
|
133 |
args:
|
134 |
num_few_shot: 0
|
135 |
metrics:
|
136 |
-
-
|
|
|
137 |
value: 8.5
|
138 |
-
name: Normalized Accuracy
|
139 |
source:
|
140 |
name: Open LLM Leaderboard
|
141 |
-
url:
|
142 |
-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=P0x0/Astra-v1-12B
|
143 |
|
144 |
- task:
|
145 |
type: text-generation
|
@@ -150,13 +148,12 @@ model-index:
|
|
150 |
args:
|
151 |
num_few_shot: 0
|
152 |
metrics:
|
153 |
-
-
|
|
|
154 |
value: 11.38
|
155 |
-
name: Normalized Accuracy
|
156 |
source:
|
157 |
name: Open LLM Leaderboard
|
158 |
-
url:
|
159 |
-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=P0x0/Astra-v1-12B
|
160 |
|
161 |
- task:
|
162 |
type: text-generation
|
@@ -169,10 +166,10 @@ model-index:
|
|
169 |
args:
|
170 |
num_few_shot: 5
|
171 |
metrics:
|
172 |
-
-
|
|
|
173 |
value: 27.34
|
174 |
-
name: Accuracy
|
175 |
source:
|
176 |
name: Open LLM Leaderboard
|
177 |
-
url:
|
178 |
-
|
|
|
65 |
name: Average
|
66 |
type: Aggregated Metrics
|
67 |
metrics:
|
68 |
+
- name: Average Score
|
69 |
+
type: average_score
|
70 |
value: 19.46
|
|
|
71 |
source:
|
72 |
name: Open LLM Leaderboard
|
73 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=P0x0/Astra-v1-12B
|
|
|
74 |
|
75 |
- task:
|
76 |
type: text-generation
|
|
|
81 |
args:
|
82 |
num_few_shot: 0
|
83 |
metrics:
|
84 |
+
- name: Strict Accuracy (Instance Level)
|
85 |
+
type: inst_level_strict_acc
|
86 |
+
value: 28.06
|
87 |
+
- name: Strict Accuracy (Prompt Level)
|
88 |
+
type: prompt_level_strict_acc
|
89 |
value: 28.06
|
|
|
90 |
source:
|
91 |
name: Open LLM Leaderboard
|
92 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=P0x0/Astra-v1-12B
|
|
|
93 |
|
94 |
- task:
|
95 |
type: text-generation
|
|
|
100 |
args:
|
101 |
num_few_shot: 3
|
102 |
metrics:
|
103 |
+
- name: Normalized Accuracy
|
104 |
+
type: acc_norm
|
105 |
value: 31.81
|
|
|
106 |
source:
|
107 |
name: Open LLM Leaderboard
|
108 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=P0x0/Astra-v1-12B
|
|
|
109 |
|
110 |
- task:
|
111 |
type: text-generation
|
|
|
116 |
args:
|
117 |
num_few_shot: 4
|
118 |
metrics:
|
119 |
+
- name: Exact Match
|
120 |
+
type: exact_match
|
121 |
value: 9.67
|
|
|
122 |
source:
|
123 |
name: Open LLM Leaderboard
|
124 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=P0x0/Astra-v1-12B
|
|
|
125 |
|
126 |
- task:
|
127 |
type: text-generation
|
|
|
132 |
args:
|
133 |
num_few_shot: 0
|
134 |
metrics:
|
135 |
+
- name: Normalized Accuracy
|
136 |
+
type: acc_norm
|
137 |
value: 8.5
|
|
|
138 |
source:
|
139 |
name: Open LLM Leaderboard
|
140 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=P0x0/Astra-v1-12B
|
|
|
141 |
|
142 |
- task:
|
143 |
type: text-generation
|
|
|
148 |
args:
|
149 |
num_few_shot: 0
|
150 |
metrics:
|
151 |
+
- name: Normalized Accuracy
|
152 |
+
type: acc_norm
|
153 |
value: 11.38
|
|
|
154 |
source:
|
155 |
name: Open LLM Leaderboard
|
156 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=P0x0/Astra-v1-12B
|
|
|
157 |
|
158 |
- task:
|
159 |
type: text-generation
|
|
|
166 |
args:
|
167 |
num_few_shot: 5
|
168 |
metrics:
|
169 |
+
- name: Accuracy
|
170 |
+
type: acc
|
171 |
value: 27.34
|
|
|
172 |
source:
|
173 |
name: Open LLM Leaderboard
|
174 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=P0x0/Astra-v1-12B
|
175 |
+
|