Hugging Face's logo

bunnycore
/
Llama-3.2-3B-Mix-Skill

Text Generation
Transformers
Safetensors
llama
mergekit
Merge
conversational
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
1
bunnycore leaderboard-pr-bot commited on
Commit
3846a10
•
1 Parent(s): 59b9c9b

Adding Evaluation Results (#1)

Browse files

- Adding Evaluation Results (78fcea9bfa859583ac1a59fb6047a64c94bc7969)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +113 -5
README.md CHANGED
@@ -1,13 +1,107 @@
1
  ---
2
- base_model:
3
- - bunnycore/Llama-3.2-3B-Long-Think
4
- - huihui-ai/Llama-3.2-3B-Instruct-abliterated
5
- - bunnycore/Llama-3.2-3B-Pure-RP
6
  library_name: transformers
7
  tags:
8
  - mergekit
9
  - merge
10
-
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  ---
12
  This language model is a merged version of several pre-trained models, designed to excel in roleplay, long-form question answering, and prompt following tasks. It was created using the TIES merge method with huihui-ai/Llama-3.2-3B-Instruct-abliterated as the base model.
13
 
@@ -58,3 +152,17 @@ parameters:
58
  dtype: float16
59
 
60
  ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
 
 
 
 
2
  library_name: transformers
3
  tags:
4
  - mergekit
5
  - merge
6
+ base_model:
7
+ - bunnycore/Llama-3.2-3B-Long-Think
8
+ - huihui-ai/Llama-3.2-3B-Instruct-abliterated
9
+ - bunnycore/Llama-3.2-3B-Pure-RP
10
+ model-index:
11
+ - name: Llama-3.2-3B-Mix-Skill
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: 64.04
24
+ name: strict accuracy
25
+ source:
26
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-Mix-Skill
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: 23.78
39
+ name: normalized accuracy
40
+ source:
41
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-Mix-Skill
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: 12.69
54
+ name: exact match
55
+ source:
56
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-Mix-Skill
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: 1.57
69
+ name: acc_norm
70
+ source:
71
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-Mix-Skill
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: 2.75
84
+ name: acc_norm
85
+ source:
86
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-Mix-Skill
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: 23.56
101
+ name: accuracy
102
+ source:
103
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-Mix-Skill
104
+ name: Open LLM Leaderboard
105
  ---
106
  This language model is a merged version of several pre-trained models, designed to excel in roleplay, long-form question answering, and prompt following tasks. It was created using the TIES merge method with huihui-ai/Llama-3.2-3B-Instruct-abliterated as the base model.
107
 
 
152
  dtype: float16
153
 
154
  ```
155
+
156
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
157
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_bunnycore__Llama-3.2-3B-Mix-Skill)
158
+
159
+ | Metric |Value|
160
+ |-------------------|----:|
161
+ |Avg. |21.40|
162
+ |IFEval (0-Shot) |64.04|
163
+ |BBH (3-Shot) |23.78|
164
+ |MATH Lvl 5 (4-Shot)|12.69|
165
+ |GPQA (0-shot) | 1.57|
166
+ |MuSR (0-shot) | 2.75|
167
+ |MMLU-PRO (5-shot) |23.56|
168
+