prithivMLmods commited on
Commit
12260c8
·
verified ·
1 Parent(s): 2839542

Adding Evaluation Results (#1)

Browse files

- Adding Evaluation Results (6a97511965cd41a08928f844b28ac8c8f3fb1b31)

Files changed (1) hide show
  1. README.md +114 -1
README.md CHANGED
@@ -10,6 +10,105 @@ tags:
10
  - Opus
11
  - text-generation-inference
12
  - Qwen
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  ---
14
  ![opus.gif](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/-vC9B4g2ccchvbS00HffZ.gif)
15
 
@@ -111,4 +210,18 @@ response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
111
  The model may struggle with adversarial or ambiguous inputs, leading to incorrect or irrelevant outputs.
112
 
113
  8. **Ethical and Safety Concerns**:
114
- Potential misuse in generating misleading, harmful, or offensive content remains a concern, and guardrails must be implemented to ensure responsible use.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  - Opus
11
  - text-generation-inference
12
  - Qwen
13
+ model-index:
14
+ - name: Calcium-Opus-20B-v1
15
+ results:
16
+ - task:
17
+ type: text-generation
18
+ name: Text Generation
19
+ dataset:
20
+ name: IFEval (0-Shot)
21
+ type: wis-k/instruction-following-eval
22
+ split: train
23
+ args:
24
+ num_few_shot: 0
25
+ metrics:
26
+ - type: inst_level_strict_acc and prompt_level_strict_acc
27
+ value: 30.93
28
+ name: averaged accuracy
29
+ source:
30
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-20B-v1
31
+ name: Open LLM Leaderboard
32
+ - task:
33
+ type: text-generation
34
+ name: Text Generation
35
+ dataset:
36
+ name: BBH (3-Shot)
37
+ type: SaylorTwift/bbh
38
+ split: test
39
+ args:
40
+ num_few_shot: 3
41
+ metrics:
42
+ - type: acc_norm
43
+ value: 41.81
44
+ name: normalized accuracy
45
+ source:
46
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-20B-v1
47
+ name: Open LLM Leaderboard
48
+ - task:
49
+ type: text-generation
50
+ name: Text Generation
51
+ dataset:
52
+ name: MATH Lvl 5 (4-Shot)
53
+ type: lighteval/MATH-Hard
54
+ split: test
55
+ args:
56
+ num_few_shot: 4
57
+ metrics:
58
+ - type: exact_match
59
+ value: 11.03
60
+ name: exact match
61
+ source:
62
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-20B-v1
63
+ name: Open LLM Leaderboard
64
+ - task:
65
+ type: text-generation
66
+ name: Text Generation
67
+ dataset:
68
+ name: GPQA (0-shot)
69
+ type: Idavidrein/gpqa
70
+ split: train
71
+ args:
72
+ num_few_shot: 0
73
+ metrics:
74
+ - type: acc_norm
75
+ value: 13.76
76
+ name: acc_norm
77
+ source:
78
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-20B-v1
79
+ name: Open LLM Leaderboard
80
+ - task:
81
+ type: text-generation
82
+ name: Text Generation
83
+ dataset:
84
+ name: MuSR (0-shot)
85
+ type: TAUR-Lab/MuSR
86
+ args:
87
+ num_few_shot: 0
88
+ metrics:
89
+ - type: acc_norm
90
+ value: 22.09
91
+ name: acc_norm
92
+ source:
93
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-20B-v1
94
+ name: Open LLM Leaderboard
95
+ - task:
96
+ type: text-generation
97
+ name: Text Generation
98
+ dataset:
99
+ name: MMLU-PRO (5-shot)
100
+ type: TIGER-Lab/MMLU-Pro
101
+ config: main
102
+ split: test
103
+ args:
104
+ num_few_shot: 5
105
+ metrics:
106
+ - type: acc
107
+ value: 41.49
108
+ name: accuracy
109
+ source:
110
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-20B-v1
111
+ name: Open LLM Leaderboard
112
  ---
113
  ![opus.gif](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/-vC9B4g2ccchvbS00HffZ.gif)
114
 
 
210
  The model may struggle with adversarial or ambiguous inputs, leading to incorrect or irrelevant outputs.
211
 
212
  8. **Ethical and Safety Concerns**:
213
+ Potential misuse in generating misleading, harmful, or offensive content remains a concern, and guardrails must be implemented to ensure responsible use.
214
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
215
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/prithivMLmods__Calcium-Opus-20B-v1-details)!
216
+ Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=prithivMLmods%2FCalcium-Opus-20B-v1&sort[column]=Average%20%E2%AC%86%EF%B8%8F&sort[direction]=desc)!
217
+
218
+ | Metric |Value (%)|
219
+ |-------------------|--------:|
220
+ |**Average** | 26.85|
221
+ |IFEval (0-Shot) | 30.93|
222
+ |BBH (3-Shot) | 41.81|
223
+ |MATH Lvl 5 (4-Shot)| 11.03|
224
+ |GPQA (0-shot) | 13.76|
225
+ |MuSR (0-shot) | 22.09|
226
+ |MMLU-PRO (5-shot) | 41.49|
227
+