Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2

#3
by Ph0enixxx - opened
Files changed (1) hide show
  1. README.md +1 -112
README.md CHANGED
@@ -1,101 +1,5 @@
1
  ---
2
  license: llama3.1
3
- model-index:
4
- - name: Llama-3.1-8B-Lexi-Uncensored-V2
5
- results:
6
- - task:
7
- type: text-generation
8
- name: Text Generation
9
- dataset:
10
- name: IFEval (0-Shot)
11
- type: HuggingFaceH4/ifeval
12
- args:
13
- num_few_shot: 0
14
- metrics:
15
- - type: inst_level_strict_acc and prompt_level_strict_acc
16
- value: 77.92
17
- name: strict accuracy
18
- source:
19
- url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
20
- name: Open LLM Leaderboard
21
- - task:
22
- type: text-generation
23
- name: Text Generation
24
- dataset:
25
- name: BBH (3-Shot)
26
- type: BBH
27
- args:
28
- num_few_shot: 3
29
- metrics:
30
- - type: acc_norm
31
- value: 29.69
32
- name: normalized accuracy
33
- source:
34
- url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
35
- name: Open LLM Leaderboard
36
- - task:
37
- type: text-generation
38
- name: Text Generation
39
- dataset:
40
- name: MATH Lvl 5 (4-Shot)
41
- type: hendrycks/competition_math
42
- args:
43
- num_few_shot: 4
44
- metrics:
45
- - type: exact_match
46
- value: 16.92
47
- name: exact match
48
- source:
49
- url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
50
- name: Open LLM Leaderboard
51
- - task:
52
- type: text-generation
53
- name: Text Generation
54
- dataset:
55
- name: GPQA (0-shot)
56
- type: Idavidrein/gpqa
57
- args:
58
- num_few_shot: 0
59
- metrics:
60
- - type: acc_norm
61
- value: 4.36
62
- name: acc_norm
63
- source:
64
- url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
65
- name: Open LLM Leaderboard
66
- - task:
67
- type: text-generation
68
- name: Text Generation
69
- dataset:
70
- name: MuSR (0-shot)
71
- type: TAUR-Lab/MuSR
72
- args:
73
- num_few_shot: 0
74
- metrics:
75
- - type: acc_norm
76
- value: 7.77
77
- name: acc_norm
78
- source:
79
- url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
80
- name: Open LLM Leaderboard
81
- - task:
82
- type: text-generation
83
- name: Text Generation
84
- dataset:
85
- name: MMLU-PRO (5-shot)
86
- type: TIGER-Lab/MMLU-Pro
87
- config: main
88
- split: test
89
- args:
90
- num_few_shot: 5
91
- metrics:
92
- - type: acc
93
- value: 30.9
94
- name: accuracy
95
- source:
96
- url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
97
- name: Open LLM Leaderboard
98
- library_name: transformers
99
  ---
100
 
101
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/644ad182f434a6a63b18eee6/7mnEJyioRzQaWz8xLM4KI.png)
@@ -104,6 +8,7 @@ VERSION 2 Update Notes:
104
  ---
105
  - More compliant
106
  - Smarter
 
107
  - For best response, use this system prompt (feel free to expand upon it as you wish):
108
 
109
  Think step by step with a logical reasoning and intellectual sense before you provide any response.
@@ -114,8 +19,6 @@ Think step by step with a logical reasoning and intellectual sense before you pr
114
  There seems to be some of the fine-tune loss happening due to the quantization. I will look into it for V3.
115
  Until then, I suggest you run F16 or Q8 if possible.
116
 
117
- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/644ad182f434a6a63b18eee6/zaHhRjsk3rvo_YewgXV2Z.png)
118
-
119
  GENERAL INFO:
120
  ---
121
 
@@ -139,17 +42,3 @@ If you find any issues or have suggestions for improvements, feel free to leave
139
 
140
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/644ad182f434a6a63b18eee6/uqJv-R1LeJEfMxi1nmTH5.png)
141
 
142
-
143
- # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
144
- Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Orenguteng__Llama-3.1-8B-Lexi-Uncensored-V2)
145
-
146
- | Metric |Value|
147
- |-------------------|----:|
148
- |Avg. |27.93|
149
- |IFEval (0-Shot) |77.92|
150
- |BBH (3-Shot) |29.69|
151
- |MATH Lvl 5 (4-Shot)|16.92|
152
- |GPQA (0-shot) | 4.36|
153
- |MuSR (0-shot) | 7.77|
154
- |MMLU-PRO (5-shot) |30.90|
155
-
 
1
  ---
2
  license: llama3.1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
4
 
5
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/644ad182f434a6a63b18eee6/7mnEJyioRzQaWz8xLM4KI.png)
 
8
  ---
9
  - More compliant
10
  - Smarter
11
+ - Not fully evaluated, but scores higher on Winogrande compared to the original instruct model. 0.77901 vs 0.78848
12
  - For best response, use this system prompt (feel free to expand upon it as you wish):
13
 
14
  Think step by step with a logical reasoning and intellectual sense before you provide any response.
 
19
  There seems to be some of the fine-tune loss happening due to the quantization. I will look into it for V3.
20
  Until then, I suggest you run F16 or Q8 if possible.
21
 
 
 
22
  GENERAL INFO:
23
  ---
24
 
 
42
 
43
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/644ad182f434a6a63b18eee6/uqJv-R1LeJEfMxi1nmTH5.png)
44