Files changed (1) hide show
  1. README.md +120 -4
README.md CHANGED
@@ -1,14 +1,117 @@
1
  ---
 
 
2
  license: mit
 
3
  datasets:
4
  - argilla/distilabel-intel-orca-dpo-pairs
5
  - jondurbin/truthy-dpo-v0.1
6
  - argilla/distilabel-math-preference-dpo
7
  - argilla/distilabel-capybara-dpo-7k-binarized
8
- language:
9
- - en
10
- library_name: adapter-transformers
11
  base_model: Technoculture/MT7Bi-sft
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  ---
13
 
14
  # Technoculture/MedMerge-6-7b-alpha-dpo
@@ -51,4 +154,17 @@ Total Size: 11.38k
51
  ### For full details of this dpo-training please read our notebook.
52
  <a target="_blank" href="https://colab.research.google.com/github/dkshjn/Technoculture/blob/main/MedMerge_6_7b_alpha_dpo.ipynb">
53
  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
54
- </a>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - en
4
  license: mit
5
+ library_name: adapter-transformers
6
  datasets:
7
  - argilla/distilabel-intel-orca-dpo-pairs
8
  - jondurbin/truthy-dpo-v0.1
9
  - argilla/distilabel-math-preference-dpo
10
  - argilla/distilabel-capybara-dpo-7k-binarized
 
 
 
11
  base_model: Technoculture/MT7Bi-sft
12
+ model-index:
13
+ - name: MedMerge-6-7b-alpha-dpo
14
+ results:
15
+ - task:
16
+ type: text-generation
17
+ name: Text Generation
18
+ dataset:
19
+ name: AI2 Reasoning Challenge (25-Shot)
20
+ type: ai2_arc
21
+ config: ARC-Challenge
22
+ split: test
23
+ args:
24
+ num_few_shot: 25
25
+ metrics:
26
+ - type: acc_norm
27
+ value: 54.27
28
+ name: normalized accuracy
29
+ source:
30
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Technoculture/MedMerge-6-7b-alpha-dpo
31
+ name: Open LLM Leaderboard
32
+ - task:
33
+ type: text-generation
34
+ name: Text Generation
35
+ dataset:
36
+ name: HellaSwag (10-Shot)
37
+ type: hellaswag
38
+ split: validation
39
+ args:
40
+ num_few_shot: 10
41
+ metrics:
42
+ - type: acc_norm
43
+ value: 75.6
44
+ name: normalized accuracy
45
+ source:
46
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Technoculture/MedMerge-6-7b-alpha-dpo
47
+ name: Open LLM Leaderboard
48
+ - task:
49
+ type: text-generation
50
+ name: Text Generation
51
+ dataset:
52
+ name: MMLU (5-Shot)
53
+ type: cais/mmlu
54
+ config: all
55
+ split: test
56
+ args:
57
+ num_few_shot: 5
58
+ metrics:
59
+ - type: acc
60
+ value: 52.65
61
+ name: accuracy
62
+ source:
63
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Technoculture/MedMerge-6-7b-alpha-dpo
64
+ name: Open LLM Leaderboard
65
+ - task:
66
+ type: text-generation
67
+ name: Text Generation
68
+ dataset:
69
+ name: TruthfulQA (0-shot)
70
+ type: truthful_qa
71
+ config: multiple_choice
72
+ split: validation
73
+ args:
74
+ num_few_shot: 0
75
+ metrics:
76
+ - type: mc2
77
+ value: 43.94
78
+ source:
79
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Technoculture/MedMerge-6-7b-alpha-dpo
80
+ name: Open LLM Leaderboard
81
+ - task:
82
+ type: text-generation
83
+ name: Text Generation
84
+ dataset:
85
+ name: Winogrande (5-shot)
86
+ type: winogrande
87
+ config: winogrande_xl
88
+ split: validation
89
+ args:
90
+ num_few_shot: 5
91
+ metrics:
92
+ - type: acc
93
+ value: 71.03
94
+ name: accuracy
95
+ source:
96
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Technoculture/MedMerge-6-7b-alpha-dpo
97
+ name: Open LLM Leaderboard
98
+ - task:
99
+ type: text-generation
100
+ name: Text Generation
101
+ dataset:
102
+ name: GSM8k (5-shot)
103
+ type: gsm8k
104
+ config: main
105
+ split: test
106
+ args:
107
+ num_few_shot: 5
108
+ metrics:
109
+ - type: acc
110
+ value: 26.16
111
+ name: accuracy
112
+ source:
113
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Technoculture/MedMerge-6-7b-alpha-dpo
114
+ name: Open LLM Leaderboard
115
  ---
116
 
117
  # Technoculture/MedMerge-6-7b-alpha-dpo
 
154
  ### For full details of this dpo-training please read our notebook.
155
  <a target="_blank" href="https://colab.research.google.com/github/dkshjn/Technoculture/blob/main/MedMerge_6_7b_alpha_dpo.ipynb">
156
  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
157
+ </a>
158
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
159
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Technoculture__MedMerge-6-7b-alpha-dpo)
160
+
161
+ | Metric |Value|
162
+ |---------------------------------|----:|
163
+ |Avg. |53.94|
164
+ |AI2 Reasoning Challenge (25-Shot)|54.27|
165
+ |HellaSwag (10-Shot) |75.60|
166
+ |MMLU (5-Shot) |52.65|
167
+ |TruthfulQA (0-shot) |43.94|
168
+ |Winogrande (5-shot) |71.03|
169
+ |GSM8k (5-shot) |26.16|
170
+