gabrielmbmb HF staff leaderboard-pr-bot commited on
Commit
d06c867
1 Parent(s): a776472

Adding Evaluation Results (#2)

Browse files

- Adding Evaluation Results (9293269c3693659b14a34522c4affbe5783e7e19)


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

Files changed (1) hide show
  1. README.md +122 -5
README.md CHANGED
@@ -1,16 +1,119 @@
1
  ---
2
- library_name: trl
3
- license: apache-2.0
4
- base_model: teknium/OpenHermes-2.5-Mistral-7B
5
- datasets:
6
- - argilla/dpo-mix-7k
7
  language:
8
  - en
 
 
9
  tags:
10
  - distilabel
11
  - dpo
12
  - rlaif
13
  - rlhf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  ---
15
 
16
  # CapybaraHermes-2.5-Mistral-7B
@@ -63,3 +166,17 @@ This is the model card of a 🤗 transformers model that has been pushed on the
63
  - **License:** Same as OpenHermes
64
  - **Finetuned from model [optional]:** [OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)
65
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
 
 
 
 
 
2
  language:
3
  - en
4
+ license: apache-2.0
5
+ library_name: trl
6
  tags:
7
  - distilabel
8
  - dpo
9
  - rlaif
10
  - rlhf
11
+ datasets:
12
+ - argilla/dpo-mix-7k
13
+ base_model: teknium/OpenHermes-2.5-Mistral-7B
14
+ model-index:
15
+ - name: CapybaraHermes-2.5-Mistral-7B
16
+ results:
17
+ - task:
18
+ type: text-generation
19
+ name: Text Generation
20
+ dataset:
21
+ name: AI2 Reasoning Challenge (25-Shot)
22
+ type: ai2_arc
23
+ config: ARC-Challenge
24
+ split: test
25
+ args:
26
+ num_few_shot: 25
27
+ metrics:
28
+ - type: acc_norm
29
+ value: 65.78
30
+ name: normalized accuracy
31
+ source:
32
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/CapybaraHermes-2.5-Mistral-7B
33
+ name: Open LLM Leaderboard
34
+ - task:
35
+ type: text-generation
36
+ name: Text Generation
37
+ dataset:
38
+ name: HellaSwag (10-Shot)
39
+ type: hellaswag
40
+ split: validation
41
+ args:
42
+ num_few_shot: 10
43
+ metrics:
44
+ - type: acc_norm
45
+ value: 85.45
46
+ name: normalized accuracy
47
+ source:
48
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/CapybaraHermes-2.5-Mistral-7B
49
+ name: Open LLM Leaderboard
50
+ - task:
51
+ type: text-generation
52
+ name: Text Generation
53
+ dataset:
54
+ name: MMLU (5-Shot)
55
+ type: cais/mmlu
56
+ config: all
57
+ split: test
58
+ args:
59
+ num_few_shot: 5
60
+ metrics:
61
+ - type: acc
62
+ value: 63.13
63
+ name: accuracy
64
+ source:
65
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/CapybaraHermes-2.5-Mistral-7B
66
+ name: Open LLM Leaderboard
67
+ - task:
68
+ type: text-generation
69
+ name: Text Generation
70
+ dataset:
71
+ name: TruthfulQA (0-shot)
72
+ type: truthful_qa
73
+ config: multiple_choice
74
+ split: validation
75
+ args:
76
+ num_few_shot: 0
77
+ metrics:
78
+ - type: mc2
79
+ value: 56.91
80
+ source:
81
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/CapybaraHermes-2.5-Mistral-7B
82
+ name: Open LLM Leaderboard
83
+ - task:
84
+ type: text-generation
85
+ name: Text Generation
86
+ dataset:
87
+ name: Winogrande (5-shot)
88
+ type: winogrande
89
+ config: winogrande_xl
90
+ split: validation
91
+ args:
92
+ num_few_shot: 5
93
+ metrics:
94
+ - type: acc
95
+ value: 78.3
96
+ name: accuracy
97
+ source:
98
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/CapybaraHermes-2.5-Mistral-7B
99
+ name: Open LLM Leaderboard
100
+ - task:
101
+ type: text-generation
102
+ name: Text Generation
103
+ dataset:
104
+ name: GSM8k (5-shot)
105
+ type: gsm8k
106
+ config: main
107
+ split: test
108
+ args:
109
+ num_few_shot: 5
110
+ metrics:
111
+ - type: acc
112
+ value: 59.29
113
+ name: accuracy
114
+ source:
115
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/CapybaraHermes-2.5-Mistral-7B
116
+ name: Open LLM Leaderboard
117
  ---
118
 
119
  # CapybaraHermes-2.5-Mistral-7B
 
166
  - **License:** Same as OpenHermes
167
  - **Finetuned from model [optional]:** [OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)
168
 
169
+
170
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
171
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_argilla__CapybaraHermes-2.5-Mistral-7B)
172
+
173
+ | Metric |Value|
174
+ |---------------------------------|----:|
175
+ |Avg. |68.14|
176
+ |AI2 Reasoning Challenge (25-Shot)|65.78|
177
+ |HellaSwag (10-Shot) |85.45|
178
+ |MMLU (5-Shot) |63.13|
179
+ |TruthfulQA (0-shot) |56.91|
180
+ |Winogrande (5-shot) |78.30|
181
+ |GSM8k (5-shot) |59.29|
182
+