T145 commited on
Commit
4f2335b
1 Parent(s): 0fa4633

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +159 -159
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
- This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
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)!