Hugging Face's logo

djuna
/
L3.1-ForStHS

Text Generation
Transformers
Safetensors
llama
mergekit
Merge
conversational
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
2
djuna leaderboard-pr-bot commited on
Commit
305aa17
•
1 Parent(s): f5442e1

Adding Evaluation Results (#2)

Browse files

- Adding Evaluation Results (5cf11c335e0bb2086f987da346baa1ac23da0a59)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

Files changed (1) hide show
  1. README.md +113 -5
README.md CHANGED
@@ -1,15 +1,109 @@
1
  ---
 
 
 
 
2
  base_model:
3
  - rityak/L3.1-FormaxGradient
4
  - vicgalle/Configurable-Llama-3.1-8B-Instruct
5
  - ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1
6
  - grimjim/Llama-3-Instruct-abliteration-LoRA-8B
7
  - DreadPoor/Heart_Stolen-8B-Model_Stock
8
- library_name: transformers
9
- tags:
10
- - mergekit
11
- - merge
12
-
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  ---
14
  # merge
15
 
@@ -40,3 +134,17 @@ merge_method: model_stock
40
  base_model: vicgalle/Configurable-Llama-3.1-8B-Instruct
41
  dtype: bfloat16
42
  ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ library_name: transformers
3
+ tags:
4
+ - mergekit
5
+ - merge
6
  base_model:
7
  - rityak/L3.1-FormaxGradient
8
  - vicgalle/Configurable-Llama-3.1-8B-Instruct
9
  - ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1
10
  - grimjim/Llama-3-Instruct-abliteration-LoRA-8B
11
  - DreadPoor/Heart_Stolen-8B-Model_Stock
12
+ model-index:
13
+ - name: L3.1-ForStHS
14
+ results:
15
+ - task:
16
+ type: text-generation
17
+ name: Text Generation
18
+ dataset:
19
+ name: IFEval (0-Shot)
20
+ type: HuggingFaceH4/ifeval
21
+ args:
22
+ num_few_shot: 0
23
+ metrics:
24
+ - type: inst_level_strict_acc and prompt_level_strict_acc
25
+ value: 78.13
26
+ name: strict accuracy
27
+ source:
28
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-ForStHS
29
+ name: Open LLM Leaderboard
30
+ - task:
31
+ type: text-generation
32
+ name: Text Generation
33
+ dataset:
34
+ name: BBH (3-Shot)
35
+ type: BBH
36
+ args:
37
+ num_few_shot: 3
38
+ metrics:
39
+ - type: acc_norm
40
+ value: 31.39
41
+ name: normalized accuracy
42
+ source:
43
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-ForStHS
44
+ name: Open LLM Leaderboard
45
+ - task:
46
+ type: text-generation
47
+ name: Text Generation
48
+ dataset:
49
+ name: MATH Lvl 5 (4-Shot)
50
+ type: hendrycks/competition_math
51
+ args:
52
+ num_few_shot: 4
53
+ metrics:
54
+ - type: exact_match
55
+ value: 12.92
56
+ name: exact match
57
+ source:
58
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-ForStHS
59
+ name: Open LLM Leaderboard
60
+ - task:
61
+ type: text-generation
62
+ name: Text Generation
63
+ dataset:
64
+ name: GPQA (0-shot)
65
+ type: Idavidrein/gpqa
66
+ args:
67
+ num_few_shot: 0
68
+ metrics:
69
+ - type: acc_norm
70
+ value: 5.48
71
+ name: acc_norm
72
+ source:
73
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-ForStHS
74
+ name: Open LLM Leaderboard
75
+ - task:
76
+ type: text-generation
77
+ name: Text Generation
78
+ dataset:
79
+ name: MuSR (0-shot)
80
+ type: TAUR-Lab/MuSR
81
+ args:
82
+ num_few_shot: 0
83
+ metrics:
84
+ - type: acc_norm
85
+ value: 9.66
86
+ name: acc_norm
87
+ source:
88
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-ForStHS
89
+ name: Open LLM Leaderboard
90
+ - task:
91
+ type: text-generation
92
+ name: Text Generation
93
+ dataset:
94
+ name: MMLU-PRO (5-shot)
95
+ type: TIGER-Lab/MMLU-Pro
96
+ config: main
97
+ split: test
98
+ args:
99
+ num_few_shot: 5
100
+ metrics:
101
+ - type: acc
102
+ value: 30.39
103
+ name: accuracy
104
+ source:
105
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-ForStHS
106
+ name: Open LLM Leaderboard
107
  ---
108
  # merge
109
 
 
134
  base_model: vicgalle/Configurable-Llama-3.1-8B-Instruct
135
  dtype: bfloat16
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_djuna__L3.1-ForStHS)
140
+
141
+ | Metric |Value|
142
+ |-------------------|----:|
143
+ |Avg. |28.00|
144
+ |IFEval (0-Shot) |78.13|
145
+ |BBH (3-Shot) |31.39|
146
+ |MATH Lvl 5 (4-Shot)|12.92|
147
+ |GPQA (0-shot) | 5.48|
148
+ |MuSR (0-shot) | 9.66|
149
+ |MMLU-PRO (5-shot) |30.39|
150
+