Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
@@ -1,15 +1,118 @@
|
|
1 |
---
|
2 |
-
license: apache-2.0
|
3 |
language:
|
4 |
- en
|
5 |
-
|
6 |
-
inference: false
|
7 |
tags:
|
8 |
- dare
|
9 |
- super mario merge
|
10 |
- pytorch
|
11 |
- solar
|
12 |
- merge
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
---
|
14 |
|
15 |
# solar megamerge 10.7b
|
@@ -60,3 +163,17 @@ python3 hf_merge.py mergelist.yaml solar-1
|
|
60 |
### Notes
|
61 |
|
62 |
* in the yaml: `p=weight` and `lambda=1/density`
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
|
|
2 |
language:
|
3 |
- en
|
4 |
+
license: apache-2.0
|
|
|
5 |
tags:
|
6 |
- dare
|
7 |
- super mario merge
|
8 |
- pytorch
|
9 |
- solar
|
10 |
- merge
|
11 |
+
pipeline_tag: text-generation
|
12 |
+
inference: false
|
13 |
+
model-index:
|
14 |
+
- name: solar-megamerge-dare-10.7b-v1
|
15 |
+
results:
|
16 |
+
- task:
|
17 |
+
type: text-generation
|
18 |
+
name: Text Generation
|
19 |
+
dataset:
|
20 |
+
name: AI2 Reasoning Challenge (25-Shot)
|
21 |
+
type: ai2_arc
|
22 |
+
config: ARC-Challenge
|
23 |
+
split: test
|
24 |
+
args:
|
25 |
+
num_few_shot: 25
|
26 |
+
metrics:
|
27 |
+
- type: acc_norm
|
28 |
+
value: 66.13
|
29 |
+
name: normalized accuracy
|
30 |
+
source:
|
31 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/solar-megamerge-dare-10.7b-v1
|
32 |
+
name: Open LLM Leaderboard
|
33 |
+
- task:
|
34 |
+
type: text-generation
|
35 |
+
name: Text Generation
|
36 |
+
dataset:
|
37 |
+
name: HellaSwag (10-Shot)
|
38 |
+
type: hellaswag
|
39 |
+
split: validation
|
40 |
+
args:
|
41 |
+
num_few_shot: 10
|
42 |
+
metrics:
|
43 |
+
- type: acc_norm
|
44 |
+
value: 85.3
|
45 |
+
name: normalized accuracy
|
46 |
+
source:
|
47 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/solar-megamerge-dare-10.7b-v1
|
48 |
+
name: Open LLM Leaderboard
|
49 |
+
- task:
|
50 |
+
type: text-generation
|
51 |
+
name: Text Generation
|
52 |
+
dataset:
|
53 |
+
name: MMLU (5-Shot)
|
54 |
+
type: cais/mmlu
|
55 |
+
config: all
|
56 |
+
split: test
|
57 |
+
args:
|
58 |
+
num_few_shot: 5
|
59 |
+
metrics:
|
60 |
+
- type: acc
|
61 |
+
value: 66.03
|
62 |
+
name: accuracy
|
63 |
+
source:
|
64 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/solar-megamerge-dare-10.7b-v1
|
65 |
+
name: Open LLM Leaderboard
|
66 |
+
- task:
|
67 |
+
type: text-generation
|
68 |
+
name: Text Generation
|
69 |
+
dataset:
|
70 |
+
name: TruthfulQA (0-shot)
|
71 |
+
type: truthful_qa
|
72 |
+
config: multiple_choice
|
73 |
+
split: validation
|
74 |
+
args:
|
75 |
+
num_few_shot: 0
|
76 |
+
metrics:
|
77 |
+
- type: mc2
|
78 |
+
value: 54.33
|
79 |
+
source:
|
80 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/solar-megamerge-dare-10.7b-v1
|
81 |
+
name: Open LLM Leaderboard
|
82 |
+
- task:
|
83 |
+
type: text-generation
|
84 |
+
name: Text Generation
|
85 |
+
dataset:
|
86 |
+
name: Winogrande (5-shot)
|
87 |
+
type: winogrande
|
88 |
+
config: winogrande_xl
|
89 |
+
split: validation
|
90 |
+
args:
|
91 |
+
num_few_shot: 5
|
92 |
+
metrics:
|
93 |
+
- type: acc
|
94 |
+
value: 82.95
|
95 |
+
name: accuracy
|
96 |
+
source:
|
97 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/solar-megamerge-dare-10.7b-v1
|
98 |
+
name: Open LLM Leaderboard
|
99 |
+
- task:
|
100 |
+
type: text-generation
|
101 |
+
name: Text Generation
|
102 |
+
dataset:
|
103 |
+
name: GSM8k (5-shot)
|
104 |
+
type: gsm8k
|
105 |
+
config: main
|
106 |
+
split: test
|
107 |
+
args:
|
108 |
+
num_few_shot: 5
|
109 |
+
metrics:
|
110 |
+
- type: acc
|
111 |
+
value: 58.0
|
112 |
+
name: accuracy
|
113 |
+
source:
|
114 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/solar-megamerge-dare-10.7b-v1
|
115 |
+
name: Open LLM Leaderboard
|
116 |
---
|
117 |
|
118 |
# solar megamerge 10.7b
|
|
|
163 |
### Notes
|
164 |
|
165 |
* in the yaml: `p=weight` and `lambda=1/density`
|
166 |
+
|
167 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
168 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_martyn__solar-megamerge-dare-10.7b-v1)
|
169 |
+
|
170 |
+
| Metric |Value|
|
171 |
+
|---------------------------------|----:|
|
172 |
+
|Avg. |68.79|
|
173 |
+
|AI2 Reasoning Challenge (25-Shot)|66.13|
|
174 |
+
|HellaSwag (10-Shot) |85.30|
|
175 |
+
|MMLU (5-Shot) |66.03|
|
176 |
+
|TruthfulQA (0-shot) |54.33|
|
177 |
+
|Winogrande (5-shot) |82.95|
|
178 |
+
|GSM8k (5-shot) |58.00|
|
179 |
+
|