lewtun HF staff commited on
Commit
b4bbb89
1 Parent(s): f1e578c

Add IFEval score to metrics

Browse files

This adds the prompt-level-loose accuracy metric from Google's IFEval benchmark: https://arxiv.org/abs/2311.07911

Files changed (1) hide show
  1. README.md +17 -0
README.md CHANGED
@@ -14,6 +14,23 @@ tags:
14
  - convAI
15
  - conversational
16
  pipeline_tag: text-generation
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
  ---
18
  # Phi-2-super (SFT + cDPO)
19
 
 
14
  - convAI
15
  - conversational
16
  pipeline_tag: text-generation
17
+ model-index:
18
+ - name: phi-2-super
19
+ results:
20
+ # IFEval
21
+ - task:
22
+ type: text-generation
23
+ name: Text Generation
24
+ dataset:
25
+ name: Instruction Following Eval
26
+ type: wis-k/instruction-following-eval
27
+ metrics:
28
+ - type: acc
29
+ name: prompt_level_loose_acc
30
+ value: 0.2717
31
+ source:
32
+ name: LightEval
33
+ url: https://github.com/huggingface/lighteval
34
  ---
35
  # Phi-2-super (SFT + cDPO)
36