Hugging Face's logo

ValiantLabs
/
Llama3.1-8B-Cobalt

Text Generation
Safetensors
English
llama
cobalt
valiant
valiant-labs
llama-3.1
llama-3.1-instruct
llama-3.1-instruct-8b
llama-3
llama-3-instruct
llama-3-instruct-8b
8b
math
math-instruct
conversational
chat
instruct
Eval Results
Model card Files
xet
Community
2
sequelbox commited on
Commit
5cee3b3
·
verified ·
1 Parent(s): 51c6fd5

eval

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -37,7 +37,7 @@ model-index:
37
  num_few_shot: 0
38
  metrics:
39
  - type: inst_level_strict_acc and prompt_level_strict_acc
40
- value: 73.94
41
  name: strict accuracy
42
  source:
43
  url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Cobalt
@@ -52,7 +52,7 @@ model-index:
52
  num_few_shot: 3
53
  metrics:
54
  - type: acc_norm
55
- value: 27.53
56
  name: normalized accuracy
57
  source:
58
  url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Cobalt
@@ -67,7 +67,7 @@ model-index:
67
  num_few_shot: 4
68
  metrics:
69
  - type: exact_match
70
- value: 15.48
71
  name: exact match
72
  source:
73
  url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Cobalt
@@ -82,7 +82,7 @@ model-index:
82
  num_few_shot: 0
83
  metrics:
84
  - type: acc_norm
85
- value: 4.47
86
  name: acc_norm
87
  source:
88
  url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Cobalt
@@ -97,7 +97,7 @@ model-index:
97
  num_few_shot: 0
98
  metrics:
99
  - type: acc_norm
100
- value: 5.08
101
  name: acc_norm
102
  source:
103
  url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Cobalt
@@ -114,7 +114,7 @@ model-index:
114
  num_few_shot: 5
115
  metrics:
116
  - type: acc
117
- value: 29.56
118
  name: accuracy
119
  source:
120
  url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Cobalt
 
37
  num_few_shot: 0
38
  metrics:
39
  - type: inst_level_strict_acc and prompt_level_strict_acc
40
+ value: 71.68
41
  name: strict accuracy
42
  source:
43
  url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Cobalt
 
52
  num_few_shot: 3
53
  metrics:
54
  - type: acc_norm
55
+ value: 27.24
56
  name: normalized accuracy
57
  source:
58
  url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Cobalt
 
67
  num_few_shot: 4
68
  metrics:
69
  - type: exact_match
70
+ value: 15.33
71
  name: exact match
72
  source:
73
  url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Cobalt
 
82
  num_few_shot: 0
83
  metrics:
84
  - type: acc_norm
85
+ value: 4.81
86
  name: acc_norm
87
  source:
88
  url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Cobalt
 
97
  num_few_shot: 0
98
  metrics:
99
  - type: acc_norm
100
+ value: 4.7
101
  name: acc_norm
102
  source:
103
  url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Cobalt
 
114
  num_few_shot: 5
115
  metrics:
116
  - type: acc
117
+ value: 29.59
118
  name: accuracy
119
  source:
120
  url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Cobalt