Hugging Face's logo

djuna
/
Q2.5-Veltha-14B

Text Generation
Transformers
Safetensors
qwen2
mergekit
Merge
conversational
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
2
djuna commited on
Commit
d9693aa
•
1 Parent(s): fd0c348

Adding Evaluation Results (#2)

Browse files

- Adding Evaluation Results (fbfbbd91dd91561cc8ef5cfbae0081a23850a476)

Files changed (1) hide show
  1. README.md +113 -5
README.md CHANGED
@@ -1,4 +1,8 @@
1
  ---
 
 
 
 
2
  base_model:
3
  - huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
4
  - EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
@@ -6,11 +10,101 @@ base_model:
6
  - qwen/Qwen2.5-14b
7
  - arcee-ai/SuperNova-Medius
8
  - allura-org/TQ2.5-14B-Aletheia-v1
9
- library_name: transformers
10
- tags:
11
- - mergekit
12
- - merge
13
-
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  ---
15
  # merge
16
 
@@ -66,3 +160,17 @@ models:
66
  weight: 8
67
  density: 0.45
68
  ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ library_name: transformers
3
+ tags:
4
+ - mergekit
5
+ - merge
6
  base_model:
7
  - huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
8
  - EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
 
10
  - qwen/Qwen2.5-14b
11
  - arcee-ai/SuperNova-Medius
12
  - allura-org/TQ2.5-14B-Aletheia-v1
13
+ model-index:
14
+ - name: Q2.5-Veltha-14B
15
+ results:
16
+ - task:
17
+ type: text-generation
18
+ name: Text Generation
19
+ dataset:
20
+ name: IFEval (0-Shot)
21
+ type: HuggingFaceH4/ifeval
22
+ args:
23
+ num_few_shot: 0
24
+ metrics:
25
+ - type: inst_level_strict_acc and prompt_level_strict_acc
26
+ value: 82.92
27
+ name: strict accuracy
28
+ source:
29
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B
30
+ name: Open LLM Leaderboard
31
+ - task:
32
+ type: text-generation
33
+ name: Text Generation
34
+ dataset:
35
+ name: BBH (3-Shot)
36
+ type: BBH
37
+ args:
38
+ num_few_shot: 3
39
+ metrics:
40
+ - type: acc_norm
41
+ value: 49.75
42
+ name: normalized accuracy
43
+ source:
44
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B
45
+ name: Open LLM Leaderboard
46
+ - task:
47
+ type: text-generation
48
+ name: Text Generation
49
+ dataset:
50
+ name: MATH Lvl 5 (4-Shot)
51
+ type: hendrycks/competition_math
52
+ args:
53
+ num_few_shot: 4
54
+ metrics:
55
+ - type: exact_match
56
+ value: 28.02
57
+ name: exact match
58
+ source:
59
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B
60
+ name: Open LLM Leaderboard
61
+ - task:
62
+ type: text-generation
63
+ name: Text Generation
64
+ dataset:
65
+ name: GPQA (0-shot)
66
+ type: Idavidrein/gpqa
67
+ args:
68
+ num_few_shot: 0
69
+ metrics:
70
+ - type: acc_norm
71
+ value: 14.54
72
+ name: acc_norm
73
+ source:
74
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B
75
+ name: Open LLM Leaderboard
76
+ - task:
77
+ type: text-generation
78
+ name: Text Generation
79
+ dataset:
80
+ name: MuSR (0-shot)
81
+ type: TAUR-Lab/MuSR
82
+ args:
83
+ num_few_shot: 0
84
+ metrics:
85
+ - type: acc_norm
86
+ value: 12.26
87
+ name: acc_norm
88
+ source:
89
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B
90
+ name: Open LLM Leaderboard
91
+ - task:
92
+ type: text-generation
93
+ name: Text Generation
94
+ dataset:
95
+ name: MMLU-PRO (5-shot)
96
+ type: TIGER-Lab/MMLU-Pro
97
+ config: main
98
+ split: test
99
+ args:
100
+ num_few_shot: 5
101
+ metrics:
102
+ - type: acc
103
+ value: 47.76
104
+ name: accuracy
105
+ source:
106
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B
107
+ name: Open LLM Leaderboard
108
  ---
109
  # merge
110
 
 
160
  weight: 8
161
  density: 0.45
162
  ```
163
+
164
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
165
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/djuna__Q2.5-Veltha-14B-details)
166
+
167
+ | Metric |Value|
168
+ |-------------------|----:|
169
+ |Avg. |39.21|
170
+ |IFEval (0-Shot) |82.92|
171
+ |BBH (3-Shot) |49.75|
172
+ |MATH Lvl 5 (4-Shot)|28.02|
173
+ |GPQA (0-shot) |14.54|
174
+ |MuSR (0-shot) |12.26|
175
+ |MMLU-PRO (5-shot) |47.76|
176
+