Files changed (1) hide show
  1. README.md +122 -8
README.md CHANGED
@@ -1,31 +1,131 @@
1
  ---
2
  language:
3
  - en
 
4
  library_name: transformers
5
- pipeline_tag: text-generation
 
 
6
  datasets:
7
  - jondurbin/airoboros-2.2
8
  - Open-Orca/OpenOrca
9
  - garage-bAInd/Open-Platypus
10
  - WizardLM/WizardLM_evol_instruct_V2_196k
11
  - TokenBender/python_eval_instruct_51k
12
- tags:
13
- - llama-2
14
- - code
15
- license: llama2
16
  model-index:
17
  - name: SpeechlessCoder
18
  results:
19
  - task:
20
  type: text-generation
21
  dataset:
22
- type: openai_humaneval
23
  name: HumanEval
 
24
  metrics:
25
- - name: pass@1
26
- type: pass@1
27
  value: 52.439
 
28
  verified: false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  ---
30
 
31
  <p><h1> speechless-coding-7b-16k-tora </h1></p>
@@ -118,3 +218,17 @@ CodeLlama-34B-Instruct: 50.79
118
 
119
  A100-40G x 4
120
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  language:
3
  - en
4
+ license: llama2
5
  library_name: transformers
6
+ tags:
7
+ - llama-2
8
+ - code
9
  datasets:
10
  - jondurbin/airoboros-2.2
11
  - Open-Orca/OpenOrca
12
  - garage-bAInd/Open-Platypus
13
  - WizardLM/WizardLM_evol_instruct_V2_196k
14
  - TokenBender/python_eval_instruct_51k
15
+ pipeline_tag: text-generation
 
 
 
16
  model-index:
17
  - name: SpeechlessCoder
18
  results:
19
  - task:
20
  type: text-generation
21
  dataset:
 
22
  name: HumanEval
23
+ type: openai_humaneval
24
  metrics:
25
+ - type: pass@1
 
26
  value: 52.439
27
+ name: pass@1
28
  verified: false
29
+ - task:
30
+ type: text-generation
31
+ name: Text Generation
32
+ dataset:
33
+ name: AI2 Reasoning Challenge (25-Shot)
34
+ type: ai2_arc
35
+ config: ARC-Challenge
36
+ split: test
37
+ args:
38
+ num_few_shot: 25
39
+ metrics:
40
+ - type: acc_norm
41
+ value: 41.13
42
+ name: normalized accuracy
43
+ source:
44
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=speechlessai/speechless-coding-7b-16k-tora
45
+ name: Open LLM Leaderboard
46
+ - task:
47
+ type: text-generation
48
+ name: Text Generation
49
+ dataset:
50
+ name: HellaSwag (10-Shot)
51
+ type: hellaswag
52
+ split: validation
53
+ args:
54
+ num_few_shot: 10
55
+ metrics:
56
+ - type: acc_norm
57
+ value: 64.48
58
+ name: normalized accuracy
59
+ source:
60
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=speechlessai/speechless-coding-7b-16k-tora
61
+ name: Open LLM Leaderboard
62
+ - task:
63
+ type: text-generation
64
+ name: Text Generation
65
+ dataset:
66
+ name: MMLU (5-Shot)
67
+ type: cais/mmlu
68
+ config: all
69
+ split: test
70
+ args:
71
+ num_few_shot: 5
72
+ metrics:
73
+ - type: acc
74
+ value: 38.86
75
+ name: accuracy
76
+ source:
77
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=speechlessai/speechless-coding-7b-16k-tora
78
+ name: Open LLM Leaderboard
79
+ - task:
80
+ type: text-generation
81
+ name: Text Generation
82
+ dataset:
83
+ name: TruthfulQA (0-shot)
84
+ type: truthful_qa
85
+ config: multiple_choice
86
+ split: validation
87
+ args:
88
+ num_few_shot: 0
89
+ metrics:
90
+ - type: mc2
91
+ value: 44.95
92
+ source:
93
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=speechlessai/speechless-coding-7b-16k-tora
94
+ name: Open LLM Leaderboard
95
+ - task:
96
+ type: text-generation
97
+ name: Text Generation
98
+ dataset:
99
+ name: Winogrande (5-shot)
100
+ type: winogrande
101
+ config: winogrande_xl
102
+ split: validation
103
+ args:
104
+ num_few_shot: 5
105
+ metrics:
106
+ - type: acc
107
+ value: 63.85
108
+ name: accuracy
109
+ source:
110
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=speechlessai/speechless-coding-7b-16k-tora
111
+ name: Open LLM Leaderboard
112
+ - task:
113
+ type: text-generation
114
+ name: Text Generation
115
+ dataset:
116
+ name: GSM8k (5-shot)
117
+ type: gsm8k
118
+ config: main
119
+ split: test
120
+ args:
121
+ num_few_shot: 5
122
+ metrics:
123
+ - type: acc
124
+ value: 17.06
125
+ name: accuracy
126
+ source:
127
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=speechlessai/speechless-coding-7b-16k-tora
128
+ name: Open LLM Leaderboard
129
  ---
130
 
131
  <p><h1> speechless-coding-7b-16k-tora </h1></p>
 
218
 
219
  A100-40G x 4
220
 
221
+
222
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
223
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_speechlessai__speechless-coding-7b-16k-tora)
224
+
225
+ | Metric |Value|
226
+ |---------------------------------|----:|
227
+ |Avg. |45.05|
228
+ |AI2 Reasoning Challenge (25-Shot)|41.13|
229
+ |HellaSwag (10-Shot) |64.48|
230
+ |MMLU (5-Shot) |38.86|
231
+ |TruthfulQA (0-shot) |44.95|
232
+ |Winogrande (5-shot) |63.85|
233
+ |GSM8k (5-shot) |17.06|
234
+