Files changed (1) hide show
  1. README.md +110 -1
README.md CHANGED
@@ -1,12 +1,107 @@
1
  ---
 
2
  library_name: transformers
3
  tags:
4
  - roleplay
5
  - rp
6
  - role
7
- license: apache-2.0
8
  datasets:
9
  - ResplendentAI/NSFW_RP_Format_DPO
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  ---
11
 
12
  # Roleplay-Llama-3-8B
@@ -39,3 +134,17 @@ For its parameter size (8B), it is actually the best performing one:
39
 
40
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5fad8602b8423e1d80b8a965/RpZs8CrDvYv5r8se4UxVu.png)
41
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: apache-2.0
3
  library_name: transformers
4
  tags:
5
  - roleplay
6
  - rp
7
  - role
 
8
  datasets:
9
  - ResplendentAI/NSFW_RP_Format_DPO
10
+ model-index:
11
+ - name: Roleplay-Llama-3-8B
12
+ results:
13
+ - task:
14
+ type: text-generation
15
+ name: Text Generation
16
+ dataset:
17
+ name: IFEval (0-Shot)
18
+ type: HuggingFaceH4/ifeval
19
+ args:
20
+ num_few_shot: 0
21
+ metrics:
22
+ - type: inst_level_strict_acc and prompt_level_strict_acc
23
+ value: 73.2
24
+ name: strict accuracy
25
+ source:
26
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/Roleplay-Llama-3-8B
27
+ name: Open LLM Leaderboard
28
+ - task:
29
+ type: text-generation
30
+ name: Text Generation
31
+ dataset:
32
+ name: BBH (3-Shot)
33
+ type: BBH
34
+ args:
35
+ num_few_shot: 3
36
+ metrics:
37
+ - type: acc_norm
38
+ value: 28.55
39
+ name: normalized accuracy
40
+ source:
41
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/Roleplay-Llama-3-8B
42
+ name: Open LLM Leaderboard
43
+ - task:
44
+ type: text-generation
45
+ name: Text Generation
46
+ dataset:
47
+ name: MATH Lvl 5 (4-Shot)
48
+ type: hendrycks/competition_math
49
+ args:
50
+ num_few_shot: 4
51
+ metrics:
52
+ - type: exact_match
53
+ value: 8.69
54
+ name: exact match
55
+ source:
56
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/Roleplay-Llama-3-8B
57
+ name: Open LLM Leaderboard
58
+ - task:
59
+ type: text-generation
60
+ name: Text Generation
61
+ dataset:
62
+ name: GPQA (0-shot)
63
+ type: Idavidrein/gpqa
64
+ args:
65
+ num_few_shot: 0
66
+ metrics:
67
+ - type: acc_norm
68
+ value: 1.45
69
+ name: acc_norm
70
+ source:
71
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/Roleplay-Llama-3-8B
72
+ name: Open LLM Leaderboard
73
+ - task:
74
+ type: text-generation
75
+ name: Text Generation
76
+ dataset:
77
+ name: MuSR (0-shot)
78
+ type: TAUR-Lab/MuSR
79
+ args:
80
+ num_few_shot: 0
81
+ metrics:
82
+ - type: acc_norm
83
+ value: 1.68
84
+ name: acc_norm
85
+ source:
86
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/Roleplay-Llama-3-8B
87
+ name: Open LLM Leaderboard
88
+ - task:
89
+ type: text-generation
90
+ name: Text Generation
91
+ dataset:
92
+ name: MMLU-PRO (5-shot)
93
+ type: TIGER-Lab/MMLU-Pro
94
+ config: main
95
+ split: test
96
+ args:
97
+ num_few_shot: 5
98
+ metrics:
99
+ - type: acc
100
+ value: 30.09
101
+ name: accuracy
102
+ source:
103
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/Roleplay-Llama-3-8B
104
+ name: Open LLM Leaderboard
105
  ---
106
 
107
  # Roleplay-Llama-3-8B
 
134
 
135
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5fad8602b8423e1d80b8a965/RpZs8CrDvYv5r8se4UxVu.png)
136
 
137
+
138
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
139
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_vicgalle__Roleplay-Llama-3-8B)
140
+
141
+ | Metric |Value|
142
+ |-------------------|----:|
143
+ |Avg. |24.33|
144
+ |IFEval (0-Shot) |73.20|
145
+ |BBH (3-Shot) |28.55|
146
+ |MATH Lvl 5 (4-Shot)| 8.69|
147
+ |GPQA (0-shot) | 1.45|
148
+ |MuSR (0-shot) | 1.68|
149
+ |MMLU-PRO (5-shot) |30.09|
150
+