Update README.md
Browse files
README.md
CHANGED
@@ -19,7 +19,8 @@ model-index:
|
|
19 |
value: 66.04
|
20 |
name: normalized accuracy
|
21 |
source:
|
22 |
-
url:
|
|
|
23 |
name: Open LLM Leaderboard
|
24 |
- task:
|
25 |
type: text-generation
|
@@ -35,7 +36,8 @@ model-index:
|
|
35 |
value: 84.31
|
36 |
name: normalized accuracy
|
37 |
source:
|
38 |
-
url:
|
|
|
39 |
name: Open LLM Leaderboard
|
40 |
- task:
|
41 |
type: text-generation
|
@@ -52,7 +54,8 @@ model-index:
|
|
52 |
value: 62.44
|
53 |
name: accuracy
|
54 |
source:
|
55 |
-
url:
|
|
|
56 |
name: Open LLM Leaderboard
|
57 |
- task:
|
58 |
type: text-generation
|
@@ -68,7 +71,8 @@ model-index:
|
|
68 |
- type: mc2
|
69 |
value: 61.71
|
70 |
source:
|
71 |
-
url:
|
|
|
72 |
name: Open LLM Leaderboard
|
73 |
- task:
|
74 |
type: text-generation
|
@@ -85,7 +89,8 @@ model-index:
|
|
85 |
value: 77.43
|
86 |
name: accuracy
|
87 |
source:
|
88 |
-
url:
|
|
|
89 |
name: Open LLM Leaderboard
|
90 |
- task:
|
91 |
type: text-generation
|
@@ -102,8 +107,11 @@ model-index:
|
|
102 |
value: 61.41
|
103 |
name: accuracy
|
104 |
source:
|
105 |
-
url:
|
|
|
106 |
name: Open LLM Leaderboard
|
|
|
|
|
107 |
---
|
108 |
|
109 |
|
@@ -118,5 +126,4 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
|
|
118 |
|MMLU (5-Shot) |62.44|
|
119 |
|TruthfulQA (0-shot) |61.71|
|
120 |
|Winogrande (5-shot) |77.43|
|
121 |
-
|GSM8k (5-shot) |61.41|
|
122 |
-
|
|
|
19 |
value: 66.04
|
20 |
name: normalized accuracy
|
21 |
source:
|
22 |
+
url: >-
|
23 |
+
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
|
24 |
name: Open LLM Leaderboard
|
25 |
- task:
|
26 |
type: text-generation
|
|
|
36 |
value: 84.31
|
37 |
name: normalized accuracy
|
38 |
source:
|
39 |
+
url: >-
|
40 |
+
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
|
41 |
name: Open LLM Leaderboard
|
42 |
- task:
|
43 |
type: text-generation
|
|
|
54 |
value: 62.44
|
55 |
name: accuracy
|
56 |
source:
|
57 |
+
url: >-
|
58 |
+
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
|
59 |
name: Open LLM Leaderboard
|
60 |
- task:
|
61 |
type: text-generation
|
|
|
71 |
- type: mc2
|
72 |
value: 61.71
|
73 |
source:
|
74 |
+
url: >-
|
75 |
+
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
|
76 |
name: Open LLM Leaderboard
|
77 |
- task:
|
78 |
type: text-generation
|
|
|
89 |
value: 77.43
|
90 |
name: accuracy
|
91 |
source:
|
92 |
+
url: >-
|
93 |
+
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
|
94 |
name: Open LLM Leaderboard
|
95 |
- task:
|
96 |
type: text-generation
|
|
|
107 |
value: 61.41
|
108 |
name: accuracy
|
109 |
source:
|
110 |
+
url: >-
|
111 |
+
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
|
112 |
name: Open LLM Leaderboard
|
113 |
+
datasets:
|
114 |
+
- vicgalle/configurable-system-prompt-multitask
|
115 |
---
|
116 |
|
117 |
|
|
|
126 |
|MMLU (5-Shot) |62.44|
|
127 |
|TruthfulQA (0-shot) |61.71|
|
128 |
|Winogrande (5-shot) |77.43|
|
129 |
+
|GSM8k (5-shot) |61.41|
|
|