Files changed (1) hide show
  1. README.md +114 -5
README.md CHANGED
@@ -1,15 +1,110 @@
1
  ---
2
- library_name: transformers
3
- license: apache-2.0
4
- license_link: https://huggingface.co/huihui-ai/Qwen2.5-7B-Instruct-abliterated/blob/main/LICENSE
5
  language:
6
  - en
7
- pipeline_tag: text-generation
8
- base_model: Qwen/Qwen2.5-7B-Instruct
9
  tags:
10
  - chat
11
  - abliterated
12
  - uncensored
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  ---
14
 
15
  # huihui-ai/Qwen2.5-7B-Instruct-abliterated
@@ -109,3 +204,17 @@ The following data has been re-evaluated and calculated as the average for each
109
 
110
  The script used for evaluation can be found inside this repository under /eval.sh, or click [here](https://huggingface.co/huihui-ai/Qwen2.5-7B-Instruct-abliterated/blob/main/eval.sh)
111
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
 
 
 
2
  language:
3
  - en
4
+ license: apache-2.0
5
+ library_name: transformers
6
  tags:
7
  - chat
8
  - abliterated
9
  - uncensored
10
+ base_model: Qwen/Qwen2.5-7B-Instruct
11
+ license_link: https://huggingface.co/huihui-ai/Qwen2.5-7B-Instruct-abliterated/blob/main/LICENSE
12
+ pipeline_tag: text-generation
13
+ model-index:
14
+ - name: Qwen2.5-7B-Instruct-abliterated
15
+ results:
16
+ - task:
17
+ type: text-generation
18
+ name: Text Generation
19
+ dataset:
20
+ name: IFEval (0-Shot)
21
+ type: HuggingFaceH4/ifeval
22
+ args:
23
+ num_few_shot: 0
24
+ metrics:
25
+ - type: inst_level_strict_acc and prompt_level_strict_acc
26
+ value: 75.46
27
+ name: strict accuracy
28
+ source:
29
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
30
+ name: Open LLM Leaderboard
31
+ - task:
32
+ type: text-generation
33
+ name: Text Generation
34
+ dataset:
35
+ name: BBH (3-Shot)
36
+ type: BBH
37
+ args:
38
+ num_few_shot: 3
39
+ metrics:
40
+ - type: acc_norm
41
+ value: 32.89
42
+ name: normalized accuracy
43
+ source:
44
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
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: hendrycks/competition_math
52
+ args:
53
+ num_few_shot: 4
54
+ metrics:
55
+ - type: exact_match
56
+ value: 0.0
57
+ name: exact match
58
+ source:
59
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
60
+ name: Open LLM Leaderboard
61
+ - task:
62
+ type: text-generation
63
+ name: Text Generation
64
+ dataset:
65
+ name: GPQA (0-shot)
66
+ type: Idavidrein/gpqa
67
+ args:
68
+ num_few_shot: 0
69
+ metrics:
70
+ - type: acc_norm
71
+ value: 8.72
72
+ name: acc_norm
73
+ source:
74
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
75
+ name: Open LLM Leaderboard
76
+ - task:
77
+ type: text-generation
78
+ name: Text Generation
79
+ dataset:
80
+ name: MuSR (0-shot)
81
+ type: TAUR-Lab/MuSR
82
+ args:
83
+ num_few_shot: 0
84
+ metrics:
85
+ - type: acc_norm
86
+ value: 7.48
87
+ name: acc_norm
88
+ source:
89
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
90
+ name: Open LLM Leaderboard
91
+ - task:
92
+ type: text-generation
93
+ name: Text Generation
94
+ dataset:
95
+ name: MMLU-PRO (5-shot)
96
+ type: TIGER-Lab/MMLU-Pro
97
+ config: main
98
+ split: test
99
+ args:
100
+ num_few_shot: 5
101
+ metrics:
102
+ - type: acc
103
+ value: 35.33
104
+ name: accuracy
105
+ source:
106
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
107
+ name: Open LLM Leaderboard
108
  ---
109
 
110
  # huihui-ai/Qwen2.5-7B-Instruct-abliterated
 
204
 
205
  The script used for evaluation can be found inside this repository under /eval.sh, or click [here](https://huggingface.co/huihui-ai/Qwen2.5-7B-Instruct-abliterated/blob/main/eval.sh)
206
 
207
+
208
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
209
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_huihui-ai__Qwen2.5-7B-Instruct-abliterated)
210
+
211
+ | Metric |Value|
212
+ |-------------------|----:|
213
+ |Avg. |26.65|
214
+ |IFEval (0-Shot) |75.46|
215
+ |BBH (3-Shot) |32.89|
216
+ |MATH Lvl 5 (4-Shot)| 0.00|
217
+ |GPQA (0-shot) | 8.72|
218
+ |MuSR (0-shot) | 7.48|
219
+ |MMLU-PRO (5-shot) |35.33|
220
+