Hugging Face's logo

Menouar
/
phi-2-basic-maths

Text Generation
PEFT
TensorBoard
Safetensors
PyTorch
English
trl
sft
Generated from Trainer
Eval Results
Model card Files Metrics Community
1
Menouar commited on
Commit
bef677a
•
1 Parent(s): 35aeae1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +42 -8
README.md CHANGED
@@ -24,10 +24,10 @@ model-index:
24
  metrics:
25
  - type: acc_norm
26
  name: normalized accuracy
27
- value: 62.03071672354948
28
  source:
29
  name: Open LLM Leaderboard
30
- url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
31
 
32
  # HellaSwag (10-shot)
33
  - task:
@@ -42,17 +42,51 @@ model-index:
42
  metrics:
43
  - type: acc_norm
44
  name: normalized accuracy
45
- value: 84.35570603465445
46
  source:
47
  name: Open LLM Leaderboard
48
- url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
49
 
50
  datasets:
51
  - gsm8k
52
- source:
53
- name: Open LLM Leaderboard
54
- url: >-
55
- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Menouar/phi-2-basic-maths
56
  language:
57
  - en
58
  pipeline_tag: text-generation
 
24
  metrics:
25
  - type: acc_norm
26
  name: normalized accuracy
27
+ value: 55.80
28
  source:
29
  name: Open LLM Leaderboard
30
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Menouar/phi-2-basic-maths
31
 
32
  # HellaSwag (10-shot)
33
  - task:
 
42
  metrics:
43
  - type: acc_norm
44
  name: normalized accuracy
45
+ value: 71.15
46
  source:
47
  name: Open LLM Leaderboard
48
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Menouar/phi-2-basic-maths
49
+
50
+ # MMLU (5-Shot)
51
+ - task:
52
+ type: text-generation
53
+ name: Text Generation
54
+ dataset:
55
+ name: MMLU (5-Shot)
56
+ type: cais/mmlu
57
+ config: all
58
+ split: test
59
+ args:
60
+ num_few_shot: 5
61
+ metrics:
62
+ - type: acc
63
+ name: accuracy
64
+ value: 47.27
65
+ source:
66
+ name: Open LLM Leaderboard
67
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Menouar/phi-2-basic-maths
68
+
69
+ # Winogrande (5-shot)
70
+ - task:
71
+ type: text-generation
72
+ name: Text Generation
73
+ dataset:
74
+ name: Winogrande (5-shot)
75
+ type: winogrande
76
+ config: winogrande_xl
77
+ split: validation
78
+ args:
79
+ num_few_shot: 5
80
+ metrics:
81
+ - type: acc
82
+ name: accuracy
83
+ value: 75.3
84
+ source:
85
+ name: Open LLM Leaderboard
86
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Menouar/phi-2-basic-maths
87
 
88
  datasets:
89
  - gsm8k
 
 
 
 
90
  language:
91
  - en
92
  pipeline_tag: text-generation