Hugging Face's logo

nbeerbower
/
Qwen2.5-Gutenberg-Doppel-14B

Text Generation
Transformers
Safetensors
qwen2
conversational
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
1
nbeerbower leaderboard-pr-bot commited on
Commit
0a34d66
•
1 Parent(s): 11a5060

Adding Evaluation Results (#1)

Browse files

- Adding Evaluation Results (fb1d9084d9b5d64f0cdff00208f73b30ef05d017)


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

Files changed (1) hide show
  1. README.md +110 -2
README.md CHANGED
@@ -1,8 +1,103 @@
1
  ---
2
- library_name: transformers
3
  license: apache-2.0
 
4
  base_model:
5
  - Qwen/Qwen2.5-14B-Instruct
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  ---
7
 
8
  ![image/png](https://huggingface.co/nbeerbower/Mistral-Small-Gutenberg-Doppel-22B/resolve/main/doppel-header?download=true)
@@ -15,4 +110,17 @@ base_model:
15
 
16
  [ORPO tuned](https://mlabonne.github.io/blog/posts/2024-04-19_Fine_tune_Llama_3_with_ORPO.html) with 4x A40 for 3 epochs.
17
 
18
- Thank you [@ParasiticRogue](https://huggingface.co/ParasiticRogue) for sponsoring.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
 
2
  license: apache-2.0
3
+ library_name: transformers
4
  base_model:
5
  - Qwen/Qwen2.5-14B-Instruct
6
+ model-index:
7
+ - name: Qwen2.5-Gutenberg-Doppel-14B
8
+ results:
9
+ - task:
10
+ type: text-generation
11
+ name: Text Generation
12
+ dataset:
13
+ name: IFEval (0-Shot)
14
+ type: HuggingFaceH4/ifeval
15
+ args:
16
+ num_few_shot: 0
17
+ metrics:
18
+ - type: inst_level_strict_acc and prompt_level_strict_acc
19
+ value: 80.91
20
+ name: strict accuracy
21
+ source:
22
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Qwen2.5-Gutenberg-Doppel-14B
23
+ name: Open LLM Leaderboard
24
+ - task:
25
+ type: text-generation
26
+ name: Text Generation
27
+ dataset:
28
+ name: BBH (3-Shot)
29
+ type: BBH
30
+ args:
31
+ num_few_shot: 3
32
+ metrics:
33
+ - type: acc_norm
34
+ value: 48.24
35
+ name: normalized accuracy
36
+ source:
37
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Qwen2.5-Gutenberg-Doppel-14B
38
+ name: Open LLM Leaderboard
39
+ - task:
40
+ type: text-generation
41
+ name: Text Generation
42
+ dataset:
43
+ name: MATH Lvl 5 (4-Shot)
44
+ type: hendrycks/competition_math
45
+ args:
46
+ num_few_shot: 4
47
+ metrics:
48
+ - type: exact_match
49
+ value: 0.0
50
+ name: exact match
51
+ source:
52
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Qwen2.5-Gutenberg-Doppel-14B
53
+ name: Open LLM Leaderboard
54
+ - task:
55
+ type: text-generation
56
+ name: Text Generation
57
+ dataset:
58
+ name: GPQA (0-shot)
59
+ type: Idavidrein/gpqa
60
+ args:
61
+ num_few_shot: 0
62
+ metrics:
63
+ - type: acc_norm
64
+ value: 11.07
65
+ name: acc_norm
66
+ source:
67
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Qwen2.5-Gutenberg-Doppel-14B
68
+ name: Open LLM Leaderboard
69
+ - task:
70
+ type: text-generation
71
+ name: Text Generation
72
+ dataset:
73
+ name: MuSR (0-shot)
74
+ type: TAUR-Lab/MuSR
75
+ args:
76
+ num_few_shot: 0
77
+ metrics:
78
+ - type: acc_norm
79
+ value: 10.02
80
+ name: acc_norm
81
+ source:
82
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Qwen2.5-Gutenberg-Doppel-14B
83
+ name: Open LLM Leaderboard
84
+ - task:
85
+ type: text-generation
86
+ name: Text Generation
87
+ dataset:
88
+ name: MMLU-PRO (5-shot)
89
+ type: TIGER-Lab/MMLU-Pro
90
+ config: main
91
+ split: test
92
+ args:
93
+ num_few_shot: 5
94
+ metrics:
95
+ - type: acc
96
+ value: 43.57
97
+ name: accuracy
98
+ source:
99
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Qwen2.5-Gutenberg-Doppel-14B
100
+ name: Open LLM Leaderboard
101
  ---
102
 
103
  ![image/png](https://huggingface.co/nbeerbower/Mistral-Small-Gutenberg-Doppel-22B/resolve/main/doppel-header?download=true)
 
110
 
111
  [ORPO tuned](https://mlabonne.github.io/blog/posts/2024-04-19_Fine_tune_Llama_3_with_ORPO.html) with 4x A40 for 3 epochs.
112
 
113
+ Thank you [@ParasiticRogue](https://huggingface.co/ParasiticRogue) for sponsoring.
114
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
115
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_nbeerbower__Qwen2.5-Gutenberg-Doppel-14B)
116
+
117
+ | Metric |Value|
118
+ |-------------------|----:|
119
+ |Avg. |32.30|
120
+ |IFEval (0-Shot) |80.91|
121
+ |BBH (3-Shot) |48.24|
122
+ |MATH Lvl 5 (4-Shot)| 0.00|
123
+ |GPQA (0-shot) |11.07|
124
+ |MuSR (0-shot) |10.02|
125
+ |MMLU-PRO (5-shot) |43.57|
126
+