Commit
7fe8c24
1 Parent(s): ca6adf3

Adding Evaluation Results (#2)

Browse files

- Adding Evaluation Results (0b48e7c64891ae0888e94814ada32eec1c793822)
- eval format (b66f8f8fccebd0eb9b9715e3c1339e141dbc9d18)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +99 -3
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  language:
3
  - en
4
- pipeline_tag: text-generation
5
  tags:
6
  - enigma
7
  - valiant
@@ -24,8 +24,103 @@ base_model: meta-llama/Llama-3.2-3B-Instruct
24
  datasets:
25
  - sequelbox/Tachibana
26
  - sequelbox/Supernova
 
27
  model_type: llama
28
- license: llama3.2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  ---
30
 
31
 
@@ -92,4 +187,5 @@ Enigma is created by [Valiant Labs.](http://valiantlabs.ca/)
92
  We care about open source.
93
  For everyone to use.
94
 
95
- We encourage others to finetune further from our models.
 
 
1
  ---
2
  language:
3
  - en
4
+ license: llama3.2
5
  tags:
6
  - enigma
7
  - valiant
 
24
  datasets:
25
  - sequelbox/Tachibana
26
  - sequelbox/Supernova
27
+ pipeline_tag: text-generation
28
  model_type: llama
29
+ model-index:
30
+ - name: Llama3.2-3B-Enigma
31
+ results:
32
+ - task:
33
+ type: text-generation
34
+ name: Text Generation
35
+ dataset:
36
+ name: IFEval (0-Shot)
37
+ type: HuggingFaceH4/ifeval
38
+ args:
39
+ num_few_shot: 0
40
+ metrics:
41
+ - type: inst_level_strict_acc and prompt_level_strict_acc
42
+ value: 47.75
43
+ name: strict accuracy
44
+ source:
45
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-Enigma
46
+ name: Open LLM Leaderboard
47
+ - task:
48
+ type: text-generation
49
+ name: Text Generation
50
+ dataset:
51
+ name: BBH (3-Shot)
52
+ type: BBH
53
+ args:
54
+ num_few_shot: 3
55
+ metrics:
56
+ - type: acc_norm
57
+ value: 18.81
58
+ name: normalized accuracy
59
+ source:
60
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-Enigma
61
+ name: Open LLM Leaderboard
62
+ - task:
63
+ type: text-generation
64
+ name: Text Generation
65
+ dataset:
66
+ name: MATH Lvl 5 (4-Shot)
67
+ type: hendrycks/competition_math
68
+ args:
69
+ num_few_shot: 4
70
+ metrics:
71
+ - type: exact_match
72
+ value: 6.65
73
+ name: exact match
74
+ source:
75
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-Enigma
76
+ name: Open LLM Leaderboard
77
+ - task:
78
+ type: text-generation
79
+ name: Text Generation
80
+ dataset:
81
+ name: GPQA (0-shot)
82
+ type: Idavidrein/gpqa
83
+ args:
84
+ num_few_shot: 0
85
+ metrics:
86
+ - type: acc_norm
87
+ value: 1.45
88
+ name: acc_norm
89
+ source:
90
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-Enigma
91
+ name: Open LLM Leaderboard
92
+ - task:
93
+ type: text-generation
94
+ name: Text Generation
95
+ dataset:
96
+ name: MuSR (0-shot)
97
+ type: TAUR-Lab/MuSR
98
+ args:
99
+ num_few_shot: 0
100
+ metrics:
101
+ - type: acc_norm
102
+ value: 4.54
103
+ name: acc_norm
104
+ source:
105
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-Enigma
106
+ name: Open LLM Leaderboard
107
+ - task:
108
+ type: text-generation
109
+ name: Text Generation
110
+ dataset:
111
+ name: MMLU-PRO (5-shot)
112
+ type: TIGER-Lab/MMLU-Pro
113
+ config: main
114
+ split: test
115
+ args:
116
+ num_few_shot: 5
117
+ metrics:
118
+ - type: acc
119
+ value: 15.41
120
+ name: accuracy
121
+ source:
122
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-Enigma
123
+ name: Open LLM Leaderboard
124
  ---
125
 
126
 
 
187
  We care about open source.
188
  For everyone to use.
189
 
190
+ We encourage others to finetune further from our models.
191
+