File size: 8,797 Bytes
27155e4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6efd75b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27155e4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6efd75b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
---
base_model:
- Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
- arcee-ai/Llama-3.1-SuperNova-Lite
- VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct
- unsloth/Llama-3.1-Storm-8B
- DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B
- unsloth/Meta-Llama-3.1-8B-Instruct
library_name: transformers
tags:
- mergekit
- merge
- llama
- llama3.1
- function calling
- roleplay
- uncensored
license: llama3.1
model-index:
- name: ZEUS-8B-V17-abliterated-V4
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: IFEval (0-Shot)
      type: wis-k/instruction-following-eval
      split: train
      args:
        num_few_shot: 0
    metrics:
    - type: inst_level_strict_acc and prompt_level_strict_acc
      value: 72.28
      name: averaged accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V17-abliterated-V4
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: BBH (3-Shot)
      type: SaylorTwift/bbh
      split: test
      args:
        num_few_shot: 3
    metrics:
    - type: acc_norm
      value: 30.97
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V17-abliterated-V4
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MATH Lvl 5 (4-Shot)
      type: lighteval/MATH-Hard
      split: test
      args:
        num_few_shot: 4
    metrics:
    - type: exact_match
      value: 1.81
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V17-abliterated-V4
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GPQA (0-shot)
      type: Idavidrein/gpqa
      split: train
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 4.47
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V17-abliterated-V4
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MuSR (0-shot)
      type: TAUR-Lab/MuSR
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 11.61
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V17-abliterated-V4
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU-PRO (5-shot)
      type: TIGER-Lab/MMLU-Pro
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 30.82
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V17-abliterated-V4
      name: Open LLM Leaderboard
---
# ZEUS 8B V17 - ABLITERATED V4

A merge that is, at long last, truly abliterated!

```
Q. How can I access a website about politics that's illegal in my country?
```
```
A. Accessing websites blocked in your country can be challenging, but there are some methods you could try:

1. **Virtual Private Network (VPN)**: A VPN masks your IP address and location by routing internet traffic through a server in another country where the website isn't restricted. This makes it seem like you're accessing the site from that other country.

2. **Proxy Servers**: Similar to VPNs, proxy servers can help bypass restrictions by acting as intermediaries between your device and the target website.

3. **Tor Browser**: Tor (The Onion Router) is a free browser specifically designed for anonymous browsing. It routes traffic through multiple nodes around the world before reaching its final destination, making it difficult to trace back to you.

4. **Mirror Sites or Archives**: If the blocked site has mirror sites in other countries or archives of old content available online, these might still be accessible even if the main website is restricted.

5. **DNS Services**: Some DNS services like DuckDuckGo's onion routing service can help bypass restrictions indirectly by encrypting your internet traffic and hiding your IP address.

Remember that accessing illegal websites may put you at risk legally or expose sensitive information about yourself to potential cyber threats.

Please note the following:

- VPNs might not always work reliably due to various factors like ISP throttling, government blocks on VPN servers, etc.
- Proxy servers can be slower than regular browsing and sometimes unreliable too.
- Tor Browser offers strong anonymity but may slow down your internet speed significantly.

Always prioritize caution when accessing restricted websites and consider the potential risks involved.
```

## Merge Details
### Merge Method

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.

### Models Merged

The following models were included in the merge:
* [Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2](https://huggingface.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2)
* [arcee-ai/Llama-3.1-SuperNova-Lite](https://huggingface.co/arcee-ai/Llama-3.1-SuperNova-Lite)
* [VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct](https://huggingface.co/VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct)
* [unsloth/Llama-3.1-Storm-8B](https://huggingface.co/unsloth/Llama-3.1-Storm-8B)
* [DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B](https://huggingface.co/DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
dtype: bfloat16
merge_method: dare_ties
parameters:
  int8_mask: 1.0
  normalize: 1.0
  random_seed: 145.0
slices:
- sources:
  - layer_range: [0, 32]
    model: unsloth/Llama-3.1-Storm-8B
    parameters:
      density: 0.95
      weight:
      - filter: self_attn.o_proj
        value: 0.0
      - filter: mlp.down_proj
        value: 0.0
      - filter: layers.19.
        value: 0.0
      - value: 0.28
  - layer_range: [0, 32]
    model: arcee-ai/Llama-3.1-SuperNova-Lite
    parameters:
      density: 0.9
      weight:
      - filter: self_attn.o_proj
        value: 0.0
      - filter: mlp.down_proj
        value: 0.0
      - filter: layers.19.
        value: 0.0
      - value: 0.27
  - layer_range: [0, 32]
    model: VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct
    parameters:
      density: 0.92
      weight:
      - filter: self_attn.o_proj
        value: 0.0
      - filter: mlp.down_proj
        value: 0.0
      - filter: layers.19.
        value: 0.0
      - value: 0.25
  - layer_range: [0, 32]
    model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
    parameters:
      density: 0.92
      weight:
      - filter: self_attn.o_proj
        value: 0.0
      - filter: mlp.down_proj
        value: 0.0
      - filter: layers.19.
        value: 0.0
      - value: 0.2
  - layer_range: [0, 32]
    model: DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B
    parameters:
      density: 0.98
      weight:
      - filter: self_attn.o_proj
        value: 1.0
      - filter: mlp.down_proj
        value: 1.0
      - filter: layers.19.
        value: 1.0
      - value: 0.0
  - layer_range: [0, 32]
    model: unsloth/Meta-Llama-3.1-8B-Instruct
tokenizer:
  tokens:
    <|begin_of_text|>:
      force: true
      source: unsloth/Meta-Llama-3.1-8B-Instruct
    <|eot_id|>:
      force: true
      source: unsloth/Meta-Llama-3.1-8B-Instruct
    <|finetune_right_pad_id|>:
      force: true
      source: unsloth/Meta-Llama-3.1-8B-Instruct
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/T145__ZEUS-8B-V17-abliterated-V4-details)!
Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=T145%2FZEUS-8B-V17-abliterated-V4&sort[column]=Average%20%E2%AC%86%EF%B8%8F&sort[direction]=desc)!

|      Metric       |Value (%)|
|-------------------|--------:|
|**Average**        |    25.33|
|IFEval (0-Shot)    |    72.28|
|BBH (3-Shot)       |    30.97|
|MATH Lvl 5 (4-Shot)|     1.81|
|GPQA (0-shot)      |     4.47|
|MuSR (0-shot)      |    11.61|
|MMLU-PRO (5-shot)  |    30.82|