Files changed (1) hide show
  1. README.md +121 -5
README.md CHANGED
@@ -1,11 +1,12 @@
1
  ---
 
 
 
 
2
  tags:
3
  - merge
4
  - mergekit
5
  - lazymergekit
6
- language:
7
- - de
8
- - en
9
  base_model:
10
  - abideen/AlphaMonarch-dora
11
  - mayflowergmbh/Wiedervereinigung-7b-dpo
@@ -21,7 +22,109 @@ base_model:
21
  - malteos/hermeo-7b
22
  - FelixChao/WestSeverus-7B-DPO-v2
23
  - cognitivecomputations/openchat-3.5-0106-laser
24
- license: cc-by-nc-4.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  ---
26
 
27
  # Spaetzle-v69-7b
@@ -184,4 +287,17 @@ pipeline = transformers.pipeline(
184
 
185
  outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
186
  print(outputs[0]["generated_text"])
187
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - de
4
+ - en
5
+ license: cc-by-nc-4.0
6
  tags:
7
  - merge
8
  - mergekit
9
  - lazymergekit
 
 
 
10
  base_model:
11
  - abideen/AlphaMonarch-dora
12
  - mayflowergmbh/Wiedervereinigung-7b-dpo
 
22
  - malteos/hermeo-7b
23
  - FelixChao/WestSeverus-7B-DPO-v2
24
  - cognitivecomputations/openchat-3.5-0106-laser
25
+ model-index:
26
+ - name: Spaetzle-v69-7b
27
+ results:
28
+ - task:
29
+ type: text-generation
30
+ name: Text Generation
31
+ dataset:
32
+ name: AI2 Reasoning Challenge (25-Shot)
33
+ type: ai2_arc
34
+ config: ARC-Challenge
35
+ split: test
36
+ args:
37
+ num_few_shot: 25
38
+ metrics:
39
+ - type: acc_norm
40
+ value: 69.54
41
+ name: normalized accuracy
42
+ source:
43
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cstr/Spaetzle-v69-7b
44
+ name: Open LLM Leaderboard
45
+ - task:
46
+ type: text-generation
47
+ name: Text Generation
48
+ dataset:
49
+ name: HellaSwag (10-Shot)
50
+ type: hellaswag
51
+ split: validation
52
+ args:
53
+ num_few_shot: 10
54
+ metrics:
55
+ - type: acc_norm
56
+ value: 86.77
57
+ name: normalized accuracy
58
+ source:
59
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cstr/Spaetzle-v69-7b
60
+ name: Open LLM Leaderboard
61
+ - task:
62
+ type: text-generation
63
+ name: Text Generation
64
+ dataset:
65
+ name: MMLU (5-Shot)
66
+ type: cais/mmlu
67
+ config: all
68
+ split: test
69
+ args:
70
+ num_few_shot: 5
71
+ metrics:
72
+ - type: acc
73
+ value: 64.63
74
+ name: accuracy
75
+ source:
76
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cstr/Spaetzle-v69-7b
77
+ name: Open LLM Leaderboard
78
+ - task:
79
+ type: text-generation
80
+ name: Text Generation
81
+ dataset:
82
+ name: TruthfulQA (0-shot)
83
+ type: truthful_qa
84
+ config: multiple_choice
85
+ split: validation
86
+ args:
87
+ num_few_shot: 0
88
+ metrics:
89
+ - type: mc2
90
+ value: 65.61
91
+ source:
92
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cstr/Spaetzle-v69-7b
93
+ name: Open LLM Leaderboard
94
+ - task:
95
+ type: text-generation
96
+ name: Text Generation
97
+ dataset:
98
+ name: Winogrande (5-shot)
99
+ type: winogrande
100
+ config: winogrande_xl
101
+ split: validation
102
+ args:
103
+ num_few_shot: 5
104
+ metrics:
105
+ - type: acc
106
+ value: 81.93
107
+ name: accuracy
108
+ source:
109
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cstr/Spaetzle-v69-7b
110
+ name: Open LLM Leaderboard
111
+ - task:
112
+ type: text-generation
113
+ name: Text Generation
114
+ dataset:
115
+ name: GSM8k (5-shot)
116
+ type: gsm8k
117
+ config: main
118
+ split: test
119
+ args:
120
+ num_few_shot: 5
121
+ metrics:
122
+ - type: acc
123
+ value: 68.76
124
+ name: accuracy
125
+ source:
126
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cstr/Spaetzle-v69-7b
127
+ name: Open LLM Leaderboard
128
  ---
129
 
130
  # Spaetzle-v69-7b
 
287
 
288
  outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
289
  print(outputs[0]["generated_text"])
290
+ ```
291
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
292
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_cstr__Spaetzle-v69-7b)
293
+
294
+ | Metric |Value|
295
+ |---------------------------------|----:|
296
+ |Avg. |72.87|
297
+ |AI2 Reasoning Challenge (25-Shot)|69.54|
298
+ |HellaSwag (10-Shot) |86.77|
299
+ |MMLU (5-Shot) |64.63|
300
+ |TruthfulQA (0-shot) |65.61|
301
+ |Winogrande (5-shot) |81.93|
302
+ |GSM8k (5-shot) |68.76|
303
+