Update README.md
Browse files
README.md
CHANGED
@@ -1,162 +1,162 @@
|
|
1 |
-
---
|
2 |
-
base_model:
|
3 |
-
- unsloth/Meta-Llama-3.1-8B-Instruct
|
4 |
-
- arcee-ai/Llama-3.1-SuperNova-Lite
|
5 |
-
- unsloth/Llama-3.1-Storm-8B
|
6 |
-
- Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
|
7 |
-
library_name: transformers
|
8 |
-
tags:
|
9 |
-
- mergekit
|
10 |
-
- merge
|
11 |
-
model-index:
|
12 |
-
- name: ZEUS-8B-V14
|
13 |
-
results:
|
14 |
-
- task:
|
15 |
-
type: text-generation
|
16 |
-
name: Text Generation
|
17 |
-
dataset:
|
18 |
-
name: IFEval (0-Shot)
|
19 |
-
type: wis-k/instruction-following-eval
|
20 |
-
split: train
|
21 |
-
args:
|
22 |
-
num_few_shot: 0
|
23 |
-
metrics:
|
24 |
-
- type: inst_level_strict_acc and prompt_level_strict_acc
|
25 |
-
value: 77.09
|
26 |
-
name: averaged accuracy
|
27 |
-
source:
|
28 |
-
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V14
|
29 |
-
name: Open LLM Leaderboard
|
30 |
-
- task:
|
31 |
-
type: text-generation
|
32 |
-
name: Text Generation
|
33 |
-
dataset:
|
34 |
-
name: BBH (3-Shot)
|
35 |
-
type: SaylorTwift/bbh
|
36 |
-
split: test
|
37 |
-
args:
|
38 |
-
num_few_shot: 3
|
39 |
-
metrics:
|
40 |
-
- type: acc_norm
|
41 |
-
value: 32.69
|
42 |
-
name: normalized accuracy
|
43 |
-
source:
|
44 |
-
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V14
|
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: lighteval/MATH-Hard
|
52 |
-
split: test
|
53 |
-
args:
|
54 |
-
num_few_shot: 4
|
55 |
-
metrics:
|
56 |
-
- type: exact_match
|
57 |
-
value: 20.47
|
58 |
-
name: exact match
|
59 |
-
source:
|
60 |
-
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V14
|
61 |
-
name: Open LLM Leaderboard
|
62 |
-
- task:
|
63 |
-
type: text-generation
|
64 |
-
name: Text Generation
|
65 |
-
dataset:
|
66 |
-
name: GPQA (0-shot)
|
67 |
-
type: Idavidrein/gpqa
|
68 |
-
split: train
|
69 |
-
args:
|
70 |
-
num_few_shot: 0
|
71 |
-
metrics:
|
72 |
-
- type: acc_norm
|
73 |
-
value: 9.4
|
74 |
-
name: acc_norm
|
75 |
-
source:
|
76 |
-
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V14
|
77 |
-
name: Open LLM Leaderboard
|
78 |
-
- task:
|
79 |
-
type: text-generation
|
80 |
-
name: Text Generation
|
81 |
-
dataset:
|
82 |
-
name: MuSR (0-shot)
|
83 |
-
type: TAUR-Lab/MuSR
|
84 |
-
args:
|
85 |
-
num_few_shot: 0
|
86 |
-
metrics:
|
87 |
-
- type: acc_norm
|
88 |
-
value: 8.29
|
89 |
-
name: acc_norm
|
90 |
-
source:
|
91 |
-
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V14
|
92 |
-
name: Open LLM Leaderboard
|
93 |
-
- task:
|
94 |
-
type: text-generation
|
95 |
-
name: Text Generation
|
96 |
-
dataset:
|
97 |
-
name: MMLU-PRO (5-shot)
|
98 |
-
type: TIGER-Lab/MMLU-Pro
|
99 |
-
config: main
|
100 |
-
split: test
|
101 |
-
args:
|
102 |
-
num_few_shot: 5
|
103 |
-
metrics:
|
104 |
-
- type: acc
|
105 |
-
value: 32.37
|
106 |
-
name: accuracy
|
107 |
-
source:
|
108 |
-
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V14
|
109 |
-
name: Open LLM Leaderboard
|
110 |
-
---
|
111 |
-
# Untitled Model (1)
|
112 |
-
|
113 |
-
|
114 |
-
|
115 |
-
## Merge Details
|
116 |
-
### Merge Method
|
117 |
-
|
118 |
-
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [unsloth/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct) as a base.
|
119 |
-
|
120 |
-
### Models Merged
|
121 |
-
|
122 |
-
The following models were included in the merge:
|
123 |
-
* [arcee-ai/Llama-3.1-SuperNova-Lite](https://huggingface.co/arcee-ai/Llama-3.1-SuperNova-Lite)
|
124 |
-
* [unsloth/Llama-3.1-Storm-8B](https://huggingface.co/unsloth/Llama-3.1-Storm-8B)
|
125 |
-
* [Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2](https://huggingface.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2)
|
126 |
-
|
127 |
-
### Configuration
|
128 |
-
|
129 |
-
The following YAML configuration was used to produce this model:
|
130 |
-
|
131 |
-
```yaml
|
132 |
-
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
|
133 |
-
dtype: bfloat16
|
134 |
-
merge_method: dare_ties
|
135 |
-
parameters:
|
136 |
-
int8_mask: 1.0
|
137 |
-
normalize: 1.0
|
138 |
-
random_seed: 145.0
|
139 |
-
slices:
|
140 |
-
- sources:
|
141 |
-
- layer_range: [0, 32]
|
142 |
-
model: unsloth/Llama-3.1-Storm-8B
|
143 |
-
parameters:
|
144 |
-
density: 0.95
|
145 |
-
weight: 0.32
|
146 |
-
- layer_range: [0, 32]
|
147 |
-
model: arcee-ai/Llama-3.1-SuperNova-Lite
|
148 |
-
parameters:
|
149 |
-
density: 0.9
|
150 |
-
weight: 0.28
|
151 |
-
- layer_range: [0, 32]
|
152 |
-
model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
|
153 |
-
parameters:
|
154 |
-
density: 0.92
|
155 |
-
weight: 0.4
|
156 |
-
- layer_range: [0, 32]
|
157 |
-
model: unsloth/Meta-Llama-3.1-8B-Instruct
|
158 |
-
tokenizer_source: union
|
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/T145__ZEUS-8B-V14-details)!
|
162 |
Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=T145%2FZEUS-8B-V14&sort[column]=Average%20%E2%AC%86%EF%B8%8F&sort[direction]=desc)!
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- unsloth/Meta-Llama-3.1-8B-Instruct
|
4 |
+
- arcee-ai/Llama-3.1-SuperNova-Lite
|
5 |
+
- unsloth/Llama-3.1-Storm-8B
|
6 |
+
- Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
|
7 |
+
library_name: transformers
|
8 |
+
tags:
|
9 |
+
- mergekit
|
10 |
+
- merge
|
11 |
+
model-index:
|
12 |
+
- name: ZEUS-8B-V14
|
13 |
+
results:
|
14 |
+
- task:
|
15 |
+
type: text-generation
|
16 |
+
name: Text Generation
|
17 |
+
dataset:
|
18 |
+
name: IFEval (0-Shot)
|
19 |
+
type: wis-k/instruction-following-eval
|
20 |
+
split: train
|
21 |
+
args:
|
22 |
+
num_few_shot: 0
|
23 |
+
metrics:
|
24 |
+
- type: inst_level_strict_acc and prompt_level_strict_acc
|
25 |
+
value: 77.09
|
26 |
+
name: averaged accuracy
|
27 |
+
source:
|
28 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V14
|
29 |
+
name: Open LLM Leaderboard
|
30 |
+
- task:
|
31 |
+
type: text-generation
|
32 |
+
name: Text Generation
|
33 |
+
dataset:
|
34 |
+
name: BBH (3-Shot)
|
35 |
+
type: SaylorTwift/bbh
|
36 |
+
split: test
|
37 |
+
args:
|
38 |
+
num_few_shot: 3
|
39 |
+
metrics:
|
40 |
+
- type: acc_norm
|
41 |
+
value: 32.69
|
42 |
+
name: normalized accuracy
|
43 |
+
source:
|
44 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V14
|
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: lighteval/MATH-Hard
|
52 |
+
split: test
|
53 |
+
args:
|
54 |
+
num_few_shot: 4
|
55 |
+
metrics:
|
56 |
+
- type: exact_match
|
57 |
+
value: 20.47
|
58 |
+
name: exact match
|
59 |
+
source:
|
60 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V14
|
61 |
+
name: Open LLM Leaderboard
|
62 |
+
- task:
|
63 |
+
type: text-generation
|
64 |
+
name: Text Generation
|
65 |
+
dataset:
|
66 |
+
name: GPQA (0-shot)
|
67 |
+
type: Idavidrein/gpqa
|
68 |
+
split: train
|
69 |
+
args:
|
70 |
+
num_few_shot: 0
|
71 |
+
metrics:
|
72 |
+
- type: acc_norm
|
73 |
+
value: 9.4
|
74 |
+
name: acc_norm
|
75 |
+
source:
|
76 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V14
|
77 |
+
name: Open LLM Leaderboard
|
78 |
+
- task:
|
79 |
+
type: text-generation
|
80 |
+
name: Text Generation
|
81 |
+
dataset:
|
82 |
+
name: MuSR (0-shot)
|
83 |
+
type: TAUR-Lab/MuSR
|
84 |
+
args:
|
85 |
+
num_few_shot: 0
|
86 |
+
metrics:
|
87 |
+
- type: acc_norm
|
88 |
+
value: 8.29
|
89 |
+
name: acc_norm
|
90 |
+
source:
|
91 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V14
|
92 |
+
name: Open LLM Leaderboard
|
93 |
+
- task:
|
94 |
+
type: text-generation
|
95 |
+
name: Text Generation
|
96 |
+
dataset:
|
97 |
+
name: MMLU-PRO (5-shot)
|
98 |
+
type: TIGER-Lab/MMLU-Pro
|
99 |
+
config: main
|
100 |
+
split: test
|
101 |
+
args:
|
102 |
+
num_few_shot: 5
|
103 |
+
metrics:
|
104 |
+
- type: acc
|
105 |
+
value: 32.37
|
106 |
+
name: accuracy
|
107 |
+
source:
|
108 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V14
|
109 |
+
name: Open LLM Leaderboard
|
110 |
+
---
|
111 |
+
# Untitled Model (1)
|
112 |
+
|
113 |
+
👎
|
114 |
+
|
115 |
+
## Merge Details
|
116 |
+
### Merge Method
|
117 |
+
|
118 |
+
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [unsloth/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct) as a base.
|
119 |
+
|
120 |
+
### Models Merged
|
121 |
+
|
122 |
+
The following models were included in the merge:
|
123 |
+
* [arcee-ai/Llama-3.1-SuperNova-Lite](https://huggingface.co/arcee-ai/Llama-3.1-SuperNova-Lite)
|
124 |
+
* [unsloth/Llama-3.1-Storm-8B](https://huggingface.co/unsloth/Llama-3.1-Storm-8B)
|
125 |
+
* [Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2](https://huggingface.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2)
|
126 |
+
|
127 |
+
### Configuration
|
128 |
+
|
129 |
+
The following YAML configuration was used to produce this model:
|
130 |
+
|
131 |
+
```yaml
|
132 |
+
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
|
133 |
+
dtype: bfloat16
|
134 |
+
merge_method: dare_ties
|
135 |
+
parameters:
|
136 |
+
int8_mask: 1.0
|
137 |
+
normalize: 1.0
|
138 |
+
random_seed: 145.0
|
139 |
+
slices:
|
140 |
+
- sources:
|
141 |
+
- layer_range: [0, 32]
|
142 |
+
model: unsloth/Llama-3.1-Storm-8B
|
143 |
+
parameters:
|
144 |
+
density: 0.95
|
145 |
+
weight: 0.32
|
146 |
+
- layer_range: [0, 32]
|
147 |
+
model: arcee-ai/Llama-3.1-SuperNova-Lite
|
148 |
+
parameters:
|
149 |
+
density: 0.9
|
150 |
+
weight: 0.28
|
151 |
+
- layer_range: [0, 32]
|
152 |
+
model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
|
153 |
+
parameters:
|
154 |
+
density: 0.92
|
155 |
+
weight: 0.4
|
156 |
+
- layer_range: [0, 32]
|
157 |
+
model: unsloth/Meta-Llama-3.1-8B-Instruct
|
158 |
+
tokenizer_source: union
|
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/T145__ZEUS-8B-V14-details)!
|
162 |
Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=T145%2FZEUS-8B-V14&sort[column]=Average%20%E2%AC%86%EF%B8%8F&sort[direction]=desc)!
|