Update README.md
Browse files
README.md
CHANGED
@@ -25,7 +25,8 @@ model-index:
|
|
25 |
value: 63.18
|
26 |
name: strict accuracy
|
27 |
source:
|
28 |
-
url:
|
|
|
29 |
name: Open LLM Leaderboard
|
30 |
- task:
|
31 |
type: text-generation
|
@@ -40,7 +41,8 @@ model-index:
|
|
40 |
value: 48.76
|
41 |
name: normalized accuracy
|
42 |
source:
|
43 |
-
url:
|
|
|
44 |
name: Open LLM Leaderboard
|
45 |
- task:
|
46 |
type: text-generation
|
@@ -55,7 +57,8 @@ model-index:
|
|
55 |
value: 31.72
|
56 |
name: exact match
|
57 |
source:
|
58 |
-
url:
|
|
|
59 |
name: Open LLM Leaderboard
|
60 |
- task:
|
61 |
type: text-generation
|
@@ -70,7 +73,8 @@ model-index:
|
|
70 |
value: 15.77
|
71 |
name: acc_norm
|
72 |
source:
|
73 |
-
url:
|
|
|
74 |
name: Open LLM Leaderboard
|
75 |
- task:
|
76 |
type: text-generation
|
@@ -85,7 +89,8 @@ model-index:
|
|
85 |
value: 17.22
|
86 |
name: acc_norm
|
87 |
source:
|
88 |
-
url:
|
|
|
89 |
name: Open LLM Leaderboard
|
90 |
- task:
|
91 |
type: text-generation
|
@@ -102,8 +107,15 @@ model-index:
|
|
102 |
value: 49.14
|
103 |
name: accuracy
|
104 |
source:
|
105 |
-
url:
|
|
|
106 |
name: Open LLM Leaderboard
|
|
|
|
|
|
|
|
|
|
|
|
|
107 |
---
|
108 |
# merge
|
109 |
|
@@ -174,4 +186,4 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
|
|
174 |
|MATH Lvl 5 (4-Shot)|31.72|
|
175 |
|GPQA (0-shot) |15.77|
|
176 |
|MuSR (0-shot) |17.22|
|
177 |
-
|MMLU-PRO (5-shot) |49.14|
|
|
|
25 |
value: 63.18
|
26 |
name: strict accuracy
|
27 |
source:
|
28 |
+
url: >-
|
29 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwestion-14B
|
30 |
name: Open LLM Leaderboard
|
31 |
- task:
|
32 |
type: text-generation
|
|
|
41 |
value: 48.76
|
42 |
name: normalized accuracy
|
43 |
source:
|
44 |
+
url: >-
|
45 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwestion-14B
|
46 |
name: Open LLM Leaderboard
|
47 |
- task:
|
48 |
type: text-generation
|
|
|
57 |
value: 31.72
|
58 |
name: exact match
|
59 |
source:
|
60 |
+
url: >-
|
61 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwestion-14B
|
62 |
name: Open LLM Leaderboard
|
63 |
- task:
|
64 |
type: text-generation
|
|
|
73 |
value: 15.77
|
74 |
name: acc_norm
|
75 |
source:
|
76 |
+
url: >-
|
77 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwestion-14B
|
78 |
name: Open LLM Leaderboard
|
79 |
- task:
|
80 |
type: text-generation
|
|
|
89 |
value: 17.22
|
90 |
name: acc_norm
|
91 |
source:
|
92 |
+
url: >-
|
93 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwestion-14B
|
94 |
name: Open LLM Leaderboard
|
95 |
- task:
|
96 |
type: text-generation
|
|
|
107 |
value: 49.14
|
108 |
name: accuracy
|
109 |
source:
|
110 |
+
url: >-
|
111 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwestion-14B
|
112 |
name: Open LLM Leaderboard
|
113 |
+
license: apache-2.0
|
114 |
+
language:
|
115 |
+
- en
|
116 |
+
metrics:
|
117 |
+
- accuracy
|
118 |
+
pipeline_tag: text-generation
|
119 |
---
|
120 |
# merge
|
121 |
|
|
|
186 |
|MATH Lvl 5 (4-Shot)|31.72|
|
187 |
|GPQA (0-shot) |15.77|
|
188 |
|MuSR (0-shot) |17.22|
|
189 |
+
|MMLU-PRO (5-shot) |49.14|
|