leaderboard-pr-bot
commited on
Commit
•
06d52a0
1
Parent(s):
79daacc
Adding Evaluation Results
Browse filesThis is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr
The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.
If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions
README.md
CHANGED
@@ -1,4 +1,9 @@
|
|
1 |
---
|
|
|
|
|
|
|
|
|
|
|
2 |
base_model:
|
3 |
- CultriX/SeQwence-14Bv1
|
4 |
- CultriX/Qwen2.5-14B-Wernicke
|
@@ -10,11 +15,101 @@ base_model:
|
|
10 |
- allknowingroger/Qwenslerp3-14B
|
11 |
- allknowingroger/Qwenslerp2-14B
|
12 |
- CultriX/Qwen2.5-14B-MergeStock
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
-
|
17 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
---
|
19 |
# merge
|
20 |
|
@@ -61,4 +156,17 @@ parameters:
|
|
61 |
dtype: bfloat16
|
62 |
tokenizer_source: Qwen/Qwen2.5-14B-Instruct
|
63 |
|
64 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: transformers
|
4 |
+
tags:
|
5 |
+
- mergekit
|
6 |
+
- merge
|
7 |
base_model:
|
8 |
- CultriX/SeQwence-14Bv1
|
9 |
- CultriX/Qwen2.5-14B-Wernicke
|
|
|
15 |
- allknowingroger/Qwenslerp3-14B
|
16 |
- allknowingroger/Qwenslerp2-14B
|
17 |
- CultriX/Qwen2.5-14B-MergeStock
|
18 |
+
model-index:
|
19 |
+
- name: QwenStock1-14B
|
20 |
+
results:
|
21 |
+
- task:
|
22 |
+
type: text-generation
|
23 |
+
name: Text Generation
|
24 |
+
dataset:
|
25 |
+
name: IFEval (0-Shot)
|
26 |
+
type: HuggingFaceH4/ifeval
|
27 |
+
args:
|
28 |
+
num_few_shot: 0
|
29 |
+
metrics:
|
30 |
+
- type: inst_level_strict_acc and prompt_level_strict_acc
|
31 |
+
value: 56.34
|
32 |
+
name: strict accuracy
|
33 |
+
source:
|
34 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/QwenStock1-14B
|
35 |
+
name: Open LLM Leaderboard
|
36 |
+
- task:
|
37 |
+
type: text-generation
|
38 |
+
name: Text Generation
|
39 |
+
dataset:
|
40 |
+
name: BBH (3-Shot)
|
41 |
+
type: BBH
|
42 |
+
args:
|
43 |
+
num_few_shot: 3
|
44 |
+
metrics:
|
45 |
+
- type: acc_norm
|
46 |
+
value: 50.08
|
47 |
+
name: normalized accuracy
|
48 |
+
source:
|
49 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/QwenStock1-14B
|
50 |
+
name: Open LLM Leaderboard
|
51 |
+
- task:
|
52 |
+
type: text-generation
|
53 |
+
name: Text Generation
|
54 |
+
dataset:
|
55 |
+
name: MATH Lvl 5 (4-Shot)
|
56 |
+
type: hendrycks/competition_math
|
57 |
+
args:
|
58 |
+
num_few_shot: 4
|
59 |
+
metrics:
|
60 |
+
- type: exact_match
|
61 |
+
value: 29.38
|
62 |
+
name: exact match
|
63 |
+
source:
|
64 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/QwenStock1-14B
|
65 |
+
name: Open LLM Leaderboard
|
66 |
+
- task:
|
67 |
+
type: text-generation
|
68 |
+
name: Text Generation
|
69 |
+
dataset:
|
70 |
+
name: GPQA (0-shot)
|
71 |
+
type: Idavidrein/gpqa
|
72 |
+
args:
|
73 |
+
num_few_shot: 0
|
74 |
+
metrics:
|
75 |
+
- type: acc_norm
|
76 |
+
value: 16.89
|
77 |
+
name: acc_norm
|
78 |
+
source:
|
79 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/QwenStock1-14B
|
80 |
+
name: Open LLM Leaderboard
|
81 |
+
- task:
|
82 |
+
type: text-generation
|
83 |
+
name: Text Generation
|
84 |
+
dataset:
|
85 |
+
name: MuSR (0-shot)
|
86 |
+
type: TAUR-Lab/MuSR
|
87 |
+
args:
|
88 |
+
num_few_shot: 0
|
89 |
+
metrics:
|
90 |
+
- type: acc_norm
|
91 |
+
value: 18.79
|
92 |
+
name: acc_norm
|
93 |
+
source:
|
94 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/QwenStock1-14B
|
95 |
+
name: Open LLM Leaderboard
|
96 |
+
- task:
|
97 |
+
type: text-generation
|
98 |
+
name: Text Generation
|
99 |
+
dataset:
|
100 |
+
name: MMLU-PRO (5-shot)
|
101 |
+
type: TIGER-Lab/MMLU-Pro
|
102 |
+
config: main
|
103 |
+
split: test
|
104 |
+
args:
|
105 |
+
num_few_shot: 5
|
106 |
+
metrics:
|
107 |
+
- type: acc
|
108 |
+
value: 49.09
|
109 |
+
name: accuracy
|
110 |
+
source:
|
111 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/QwenStock1-14B
|
112 |
+
name: Open LLM Leaderboard
|
113 |
---
|
114 |
# merge
|
115 |
|
|
|
156 |
dtype: bfloat16
|
157 |
tokenizer_source: Qwen/Qwen2.5-14B-Instruct
|
158 |
|
159 |
+
```
|
160 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
161 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_allknowingroger__QwenStock1-14B)
|
162 |
+
|
163 |
+
| Metric |Value|
|
164 |
+
|-------------------|----:|
|
165 |
+
|Avg. |36.76|
|
166 |
+
|IFEval (0-Shot) |56.34|
|
167 |
+
|BBH (3-Shot) |50.08|
|
168 |
+
|MATH Lvl 5 (4-Shot)|29.38|
|
169 |
+
|GPQA (0-shot) |16.89|
|
170 |
+
|MuSR (0-shot) |18.79|
|
171 |
+
|MMLU-PRO (5-shot) |49.09|
|
172 |
+
|