Hugging Face's logo

Quazim0t0
/
Phi4-ODB-14b-GGUF.q4_k_m

GGUF
Eval Results
Inference Endpoints
conversational
Model card Files Community
Quazim0t0 commited on
Commit
3811d3a
·
verified ·
1 Parent(s): b2dada8

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +114 -0
README.md ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ model-index:
3
+ - name: ODB-14b-sce
4
+ results:
5
+ - task:
6
+ type: text-generation
7
+ name: Text Generation
8
+ dataset:
9
+ name: IFEval (0-Shot)
10
+ type: HuggingFaceH4/ifeval
11
+ args:
12
+ num_few_shot: 0
13
+ metrics:
14
+ - type: inst_level_strict_acc and prompt_level_strict_acc
15
+ value: 70.16
16
+ name: strict accuracy
17
+ source:
18
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Quazim0t0/ODB-14b-sce
19
+ name: Open LLM Leaderboard
20
+ - task:
21
+ type: text-generation
22
+ name: Text Generation
23
+ dataset:
24
+ name: BBH (3-Shot)
25
+ type: BBH
26
+ args:
27
+ num_few_shot: 3
28
+ metrics:
29
+ - type: acc_norm
30
+ value: 56.19
31
+ name: normalized accuracy
32
+ source:
33
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Quazim0t0/ODB-14b-sce
34
+ name: Open LLM Leaderboard
35
+ - task:
36
+ type: text-generation
37
+ name: Text Generation
38
+ dataset:
39
+ name: MATH Lvl 5 (4-Shot)
40
+ type: hendrycks/competition_math
41
+ args:
42
+ num_few_shot: 4
43
+ metrics:
44
+ - type: exact_match
45
+ value: 41.16
46
+ name: exact match
47
+ source:
48
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Quazim0t0/ODB-14b-sce
49
+ name: Open LLM Leaderboard
50
+ - task:
51
+ type: text-generation
52
+ name: Text Generation
53
+ dataset:
54
+ name: GPQA (0-shot)
55
+ type: Idavidrein/gpqa
56
+ args:
57
+ num_few_shot: 0
58
+ metrics:
59
+ - type: acc_norm
60
+ value: 14.99
61
+ name: acc_norm
62
+ source:
63
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Quazim0t0/ODB-14b-sce
64
+ name: Open LLM Leaderboard
65
+ - task:
66
+ type: text-generation
67
+ name: Text Generation
68
+ dataset:
69
+ name: MuSR (0-shot)
70
+ type: TAUR-Lab/MuSR
71
+ args:
72
+ num_few_shot: 0
73
+ metrics:
74
+ - type: acc_norm
75
+ value: 16.5
76
+ name: acc_norm
77
+ source:
78
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Quazim0t0/ODB-14b-sce
79
+ name: Open LLM Leaderboard
80
+ - task:
81
+ type: text-generation
82
+ name: Text Generation
83
+ dataset:
84
+ name: MMLU-PRO (5-shot)
85
+ type: TIGER-Lab/MMLU-Pro
86
+ config: main
87
+ split: test
88
+ args:
89
+ num_few_shot: 5
90
+ metrics:
91
+ - type: acc
92
+ value: 49.02
93
+ name: accuracy
94
+ source:
95
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Quazim0t0/ODB-14b-sce
96
+ name: Open LLM Leaderboard
97
+ ---
98
+ This is a Microsoft Phi4 Model that can be used a base. The score will probably be passed by another soon enough but as of
99
+ # 2/6/2025
100
+ The model has placed
101
+ # #51
102
+ on the OpenLLM Leaderboards
103
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
104
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/Quazim0t0__ODB-14b-sce-details)
105
+
106
+ | Metric |Value|
107
+ |-------------------|----:|
108
+ |Avg. |41.34|
109
+ |IFEval (0-Shot) |70.16|
110
+ |BBH (3-Shot) |56.19|
111
+ |MATH Lvl 5 (4-Shot)|41.16|
112
+ |GPQA (0-shot) |14.99|
113
+ |MuSR (0-shot) |16.50|
114
+ |MMLU-PRO (5-shot) |49.02|