Update README.md
Browse files
README.md
CHANGED
@@ -9,6 +9,10 @@ tags:
|
|
9 |
- transformers
|
10 |
- llama
|
11 |
- instruction-tuning
|
|
|
|
|
|
|
|
|
12 |
license: apache-2.0
|
13 |
language:
|
14 |
- en
|
@@ -34,7 +38,8 @@ model-index:
|
|
34 |
value: 69.31
|
35 |
name: averaged accuracy
|
36 |
source:
|
37 |
-
url:
|
|
|
38 |
name: Open LLM Leaderboard
|
39 |
- task:
|
40 |
type: text-generation
|
@@ -50,7 +55,8 @@ model-index:
|
|
50 |
value: 52.12
|
51 |
name: normalized accuracy
|
52 |
source:
|
53 |
-
url:
|
|
|
54 |
name: Open LLM Leaderboard
|
55 |
- task:
|
56 |
type: text-generation
|
@@ -66,7 +72,8 @@ model-index:
|
|
66 |
value: 39.58
|
67 |
name: exact match
|
68 |
source:
|
69 |
-
url:
|
|
|
70 |
name: Open LLM Leaderboard
|
71 |
- task:
|
72 |
type: text-generation
|
@@ -82,7 +89,8 @@ model-index:
|
|
82 |
value: 26.06
|
83 |
name: acc_norm
|
84 |
source:
|
85 |
-
url:
|
|
|
86 |
name: Open LLM Leaderboard
|
87 |
- task:
|
88 |
type: text-generation
|
@@ -97,7 +105,8 @@ model-index:
|
|
97 |
value: 21.4
|
98 |
name: acc_norm
|
99 |
source:
|
100 |
-
url:
|
|
|
101 |
name: Open LLM Leaderboard
|
102 |
- task:
|
103 |
type: text-generation
|
@@ -114,8 +123,13 @@ model-index:
|
|
114 |
value: 46.37
|
115 |
name: accuracy
|
116 |
source:
|
117 |
-
url:
|
|
|
118 |
name: Open LLM Leaderboard
|
|
|
|
|
|
|
|
|
119 |
---
|
120 |

|
121 |
|
@@ -211,5 +225,4 @@ Summarized results can be found [here](https://huggingface.co/datasets/open-llm-
|
|
211 |
|MATH Lvl 5 (4-Shot)| 39.58|
|
212 |
|GPQA (0-shot) | 26.06|
|
213 |
|MuSR (0-shot) | 21.40|
|
214 |
-
|MMLU-PRO (5-shot) | 46.37|
|
215 |
-
|
|
|
9 |
- transformers
|
10 |
- llama
|
11 |
- instruction-tuning
|
12 |
+
- cot
|
13 |
+
- RL
|
14 |
+
- research
|
15 |
+
- SOTA
|
16 |
license: apache-2.0
|
17 |
language:
|
18 |
- en
|
|
|
38 |
value: 69.31
|
39 |
name: averaged accuracy
|
40 |
source:
|
41 |
+
url: >-
|
42 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Daemontatox%2FLlama3.3-70B-CogniLink
|
43 |
name: Open LLM Leaderboard
|
44 |
- task:
|
45 |
type: text-generation
|
|
|
55 |
value: 52.12
|
56 |
name: normalized accuracy
|
57 |
source:
|
58 |
+
url: >-
|
59 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Daemontatox%2FLlama3.3-70B-CogniLink
|
60 |
name: Open LLM Leaderboard
|
61 |
- task:
|
62 |
type: text-generation
|
|
|
72 |
value: 39.58
|
73 |
name: exact match
|
74 |
source:
|
75 |
+
url: >-
|
76 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Daemontatox%2FLlama3.3-70B-CogniLink
|
77 |
name: Open LLM Leaderboard
|
78 |
- task:
|
79 |
type: text-generation
|
|
|
89 |
value: 26.06
|
90 |
name: acc_norm
|
91 |
source:
|
92 |
+
url: >-
|
93 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Daemontatox%2FLlama3.3-70B-CogniLink
|
94 |
name: Open LLM Leaderboard
|
95 |
- task:
|
96 |
type: text-generation
|
|
|
105 |
value: 21.4
|
106 |
name: acc_norm
|
107 |
source:
|
108 |
+
url: >-
|
109 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Daemontatox%2FLlama3.3-70B-CogniLink
|
110 |
name: Open LLM Leaderboard
|
111 |
- task:
|
112 |
type: text-generation
|
|
|
123 |
value: 46.37
|
124 |
name: accuracy
|
125 |
source:
|
126 |
+
url: >-
|
127 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Daemontatox%2FLlama3.3-70B-CogniLink
|
128 |
name: Open LLM Leaderboard
|
129 |
+
metrics:
|
130 |
+
- accuracy
|
131 |
+
- bleu
|
132 |
+
- code_eval
|
133 |
---
|
134 |

|
135 |
|
|
|
225 |
|MATH Lvl 5 (4-Shot)| 39.58|
|
226 |
|GPQA (0-shot) | 26.06|
|
227 |
|MuSR (0-shot) | 21.40|
|
228 |
+
|MMLU-PRO (5-shot) | 46.37|
|
|