Adding Evaluation Results (#2)
Browse files- Adding Evaluation Results (335ba8faeb0222299d79fe4c15151291852dd002)
README.md
CHANGED
@@ -1,15 +1,109 @@
|
|
1 |
---
|
|
|
|
|
|
|
|
|
2 |
base_model:
|
3 |
- arcee-ai/SuperNova-Medius
|
4 |
- huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
|
5 |
- allura-org/TQ2.5-14B-Aletheia-v1
|
6 |
- EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
|
7 |
- v000000/Qwen2.5-Lumen-14B
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
-
|
12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
---
|
14 |
# merge
|
15 |
|
@@ -65,3 +159,17 @@ models:
|
|
65 |
density: 0.45
|
66 |
|
67 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
library_name: transformers
|
3 |
+
tags:
|
4 |
+
- mergekit
|
5 |
+
- merge
|
6 |
base_model:
|
7 |
- arcee-ai/SuperNova-Medius
|
8 |
- huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
|
9 |
- allura-org/TQ2.5-14B-Aletheia-v1
|
10 |
- EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
|
11 |
- v000000/Qwen2.5-Lumen-14B
|
12 |
+
model-index:
|
13 |
+
- name: Q2.5-Veltha-14B-0.5
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
type: text-generation
|
17 |
+
name: Text Generation
|
18 |
+
dataset:
|
19 |
+
name: IFEval (0-Shot)
|
20 |
+
type: HuggingFaceH4/ifeval
|
21 |
+
args:
|
22 |
+
num_few_shot: 0
|
23 |
+
metrics:
|
24 |
+
- type: inst_level_strict_acc and prompt_level_strict_acc
|
25 |
+
value: 77.96
|
26 |
+
name: strict accuracy
|
27 |
+
source:
|
28 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B-0.5
|
29 |
+
name: Open LLM Leaderboard
|
30 |
+
- task:
|
31 |
+
type: text-generation
|
32 |
+
name: Text Generation
|
33 |
+
dataset:
|
34 |
+
name: BBH (3-Shot)
|
35 |
+
type: BBH
|
36 |
+
args:
|
37 |
+
num_few_shot: 3
|
38 |
+
metrics:
|
39 |
+
- type: acc_norm
|
40 |
+
value: 50.32
|
41 |
+
name: normalized accuracy
|
42 |
+
source:
|
43 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B-0.5
|
44 |
+
name: Open LLM Leaderboard
|
45 |
+
- task:
|
46 |
+
type: text-generation
|
47 |
+
name: Text Generation
|
48 |
+
dataset:
|
49 |
+
name: MATH Lvl 5 (4-Shot)
|
50 |
+
type: hendrycks/competition_math
|
51 |
+
args:
|
52 |
+
num_few_shot: 4
|
53 |
+
metrics:
|
54 |
+
- type: exact_match
|
55 |
+
value: 33.84
|
56 |
+
name: exact match
|
57 |
+
source:
|
58 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B-0.5
|
59 |
+
name: Open LLM Leaderboard
|
60 |
+
- task:
|
61 |
+
type: text-generation
|
62 |
+
name: Text Generation
|
63 |
+
dataset:
|
64 |
+
name: GPQA (0-shot)
|
65 |
+
type: Idavidrein/gpqa
|
66 |
+
args:
|
67 |
+
num_few_shot: 0
|
68 |
+
metrics:
|
69 |
+
- type: acc_norm
|
70 |
+
value: 15.77
|
71 |
+
name: acc_norm
|
72 |
+
source:
|
73 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B-0.5
|
74 |
+
name: Open LLM Leaderboard
|
75 |
+
- task:
|
76 |
+
type: text-generation
|
77 |
+
name: Text Generation
|
78 |
+
dataset:
|
79 |
+
name: MuSR (0-shot)
|
80 |
+
type: TAUR-Lab/MuSR
|
81 |
+
args:
|
82 |
+
num_few_shot: 0
|
83 |
+
metrics:
|
84 |
+
- type: acc_norm
|
85 |
+
value: 14.17
|
86 |
+
name: acc_norm
|
87 |
+
source:
|
88 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B-0.5
|
89 |
+
name: Open LLM Leaderboard
|
90 |
+
- task:
|
91 |
+
type: text-generation
|
92 |
+
name: Text Generation
|
93 |
+
dataset:
|
94 |
+
name: MMLU-PRO (5-shot)
|
95 |
+
type: TIGER-Lab/MMLU-Pro
|
96 |
+
config: main
|
97 |
+
split: test
|
98 |
+
args:
|
99 |
+
num_few_shot: 5
|
100 |
+
metrics:
|
101 |
+
- type: acc
|
102 |
+
value: 47.72
|
103 |
+
name: accuracy
|
104 |
+
source:
|
105 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B-0.5
|
106 |
+
name: Open LLM Leaderboard
|
107 |
---
|
108 |
# merge
|
109 |
|
|
|
159 |
density: 0.45
|
160 |
|
161 |
```
|
162 |
+
|
163 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
164 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/djuna__Q2.5-Veltha-14B-0.5-details)
|
165 |
+
|
166 |
+
| Metric |Value|
|
167 |
+
|-------------------|----:|
|
168 |
+
|Avg. |39.96|
|
169 |
+
|IFEval (0-Shot) |77.96|
|
170 |
+
|BBH (3-Shot) |50.32|
|
171 |
+
|MATH Lvl 5 (4-Shot)|33.84|
|
172 |
+
|GPQA (0-shot) |15.77|
|
173 |
+
|MuSR (0-shot) |14.17|
|
174 |
+
|MMLU-PRO (5-shot) |47.72|
|
175 |
+
|