bedio commited on
Commit
7870bad
1 Parent(s): 304e293

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +18 -9
README.md CHANGED
@@ -1,6 +1,5 @@
1
  ---
2
  library_name: transformers
3
- tags: []
4
  model-index:
5
  - name: Explore_Llama-3.1-8B-Inst
6
  results:
@@ -17,7 +16,8 @@ model-index:
17
  value: 77.95
18
  name: strict accuracy
19
  source:
20
- url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.1-8B-Inst
 
21
  name: Open LLM Leaderboard
22
  - task:
23
  type: text-generation
@@ -32,7 +32,8 @@ model-index:
32
  value: 30.39
33
  name: normalized accuracy
34
  source:
35
- url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.1-8B-Inst
 
36
  name: Open LLM Leaderboard
37
  - task:
38
  type: text-generation
@@ -47,7 +48,8 @@ model-index:
47
  value: 17.52
48
  name: exact match
49
  source:
50
- url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.1-8B-Inst
 
51
  name: Open LLM Leaderboard
52
  - task:
53
  type: text-generation
@@ -62,7 +64,8 @@ model-index:
62
  value: 4.47
63
  name: acc_norm
64
  source:
65
- url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.1-8B-Inst
 
66
  name: Open LLM Leaderboard
67
  - task:
68
  type: text-generation
@@ -77,7 +80,8 @@ model-index:
77
  value: 9.64
78
  name: acc_norm
79
  source:
80
- url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.1-8B-Inst
 
81
  name: Open LLM Leaderboard
82
  - task:
83
  type: text-generation
@@ -94,8 +98,14 @@ model-index:
94
  value: 31.02
95
  name: accuracy
96
  source:
97
- url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.1-8B-Inst
 
98
  name: Open LLM Leaderboard
 
 
 
 
 
99
  ---
100
 
101
  # Model Card for Model ID
@@ -310,5 +320,4 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
310
  |MATH Lvl 5 (4-Shot)|17.52|
311
  |GPQA (0-shot) | 4.47|
312
  |MuSR (0-shot) | 9.64|
313
- |MMLU-PRO (5-shot) |31.02|
314
-
 
1
  ---
2
  library_name: transformers
 
3
  model-index:
4
  - name: Explore_Llama-3.1-8B-Inst
5
  results:
 
16
  value: 77.95
17
  name: strict accuracy
18
  source:
19
+ url: >-
20
+ https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.1-8B-Inst
21
  name: Open LLM Leaderboard
22
  - task:
23
  type: text-generation
 
32
  value: 30.39
33
  name: normalized accuracy
34
  source:
35
+ url: >-
36
+ https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.1-8B-Inst
37
  name: Open LLM Leaderboard
38
  - task:
39
  type: text-generation
 
48
  value: 17.52
49
  name: exact match
50
  source:
51
+ url: >-
52
+ https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.1-8B-Inst
53
  name: Open LLM Leaderboard
54
  - task:
55
  type: text-generation
 
64
  value: 4.47
65
  name: acc_norm
66
  source:
67
+ url: >-
68
+ https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.1-8B-Inst
69
  name: Open LLM Leaderboard
70
  - task:
71
  type: text-generation
 
80
  value: 9.64
81
  name: acc_norm
82
  source:
83
+ url: >-
84
+ https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.1-8B-Inst
85
  name: Open LLM Leaderboard
86
  - task:
87
  type: text-generation
 
98
  value: 31.02
99
  name: accuracy
100
  source:
101
+ url: >-
102
+ https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.1-8B-Inst
103
  name: Open LLM Leaderboard
104
+ license: apache-2.0
105
+ language:
106
+ - en
107
+ base_model:
108
+ - meta-llama/Llama-3.1-8B-Instruct
109
  ---
110
 
111
  # Model Card for Model ID
 
320
  |MATH Lvl 5 (4-Shot)|17.52|
321
  |GPQA (0-shot) | 4.47|
322
  |MuSR (0-shot) | 9.64|
323
+ |MMLU-PRO (5-shot) |31.02|