Files changed (1) hide show
  1. README.md +121 -5
README.md CHANGED
@@ -1,12 +1,115 @@
1
  ---
 
 
 
 
2
  base_model:
3
  - meta-llama/Llama-2-70b-hf
4
  - codellama/CodeLlama-70b-Python-hf
5
  - codellama/CodeLlama-70b-Instruct-hf
6
- tags:
7
- - mergekit
8
- - merge
9
- license: mit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  ---
11
  # Codellama-python-instruct
12
 
@@ -45,4 +148,17 @@ parameters:
45
  # int8_mask: true
46
  dtype: float16
47
 
48
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: mit
3
+ tags:
4
+ - mergekit
5
+ - merge
6
  base_model:
7
  - meta-llama/Llama-2-70b-hf
8
  - codellama/CodeLlama-70b-Python-hf
9
  - codellama/CodeLlama-70b-Instruct-hf
10
+ model-index:
11
+ - name: code-llama-70b-python-instruct
12
+ results:
13
+ - task:
14
+ type: text-generation
15
+ name: Text Generation
16
+ dataset:
17
+ name: AI2 Reasoning Challenge (25-Shot)
18
+ type: ai2_arc
19
+ config: ARC-Challenge
20
+ split: test
21
+ args:
22
+ num_few_shot: 25
23
+ metrics:
24
+ - type: acc_norm
25
+ value: 29.61
26
+ name: normalized accuracy
27
+ source:
28
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NobodyExistsOnTheInternet/code-llama-70b-python-instruct
29
+ name: Open LLM Leaderboard
30
+ - task:
31
+ type: text-generation
32
+ name: Text Generation
33
+ dataset:
34
+ name: HellaSwag (10-Shot)
35
+ type: hellaswag
36
+ split: validation
37
+ args:
38
+ num_few_shot: 10
39
+ metrics:
40
+ - type: acc_norm
41
+ value: 25.66
42
+ name: normalized accuracy
43
+ source:
44
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NobodyExistsOnTheInternet/code-llama-70b-python-instruct
45
+ name: Open LLM Leaderboard
46
+ - task:
47
+ type: text-generation
48
+ name: Text Generation
49
+ dataset:
50
+ name: MMLU (5-Shot)
51
+ type: cais/mmlu
52
+ config: all
53
+ split: test
54
+ args:
55
+ num_few_shot: 5
56
+ metrics:
57
+ - type: acc
58
+ value: 23.5
59
+ name: accuracy
60
+ source:
61
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NobodyExistsOnTheInternet/code-llama-70b-python-instruct
62
+ name: Open LLM Leaderboard
63
+ - task:
64
+ type: text-generation
65
+ name: Text Generation
66
+ dataset:
67
+ name: TruthfulQA (0-shot)
68
+ type: truthful_qa
69
+ config: multiple_choice
70
+ split: validation
71
+ args:
72
+ num_few_shot: 0
73
+ metrics:
74
+ - type: mc2
75
+ value: 49.26
76
+ source:
77
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NobodyExistsOnTheInternet/code-llama-70b-python-instruct
78
+ name: Open LLM Leaderboard
79
+ - task:
80
+ type: text-generation
81
+ name: Text Generation
82
+ dataset:
83
+ name: Winogrande (5-shot)
84
+ type: winogrande
85
+ config: winogrande_xl
86
+ split: validation
87
+ args:
88
+ num_few_shot: 5
89
+ metrics:
90
+ - type: acc
91
+ value: 49.25
92
+ name: accuracy
93
+ source:
94
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NobodyExistsOnTheInternet/code-llama-70b-python-instruct
95
+ name: Open LLM Leaderboard
96
+ - task:
97
+ type: text-generation
98
+ name: Text Generation
99
+ dataset:
100
+ name: GSM8k (5-shot)
101
+ type: gsm8k
102
+ config: main
103
+ split: test
104
+ args:
105
+ num_few_shot: 5
106
+ metrics:
107
+ - type: acc
108
+ value: 0.0
109
+ name: accuracy
110
+ source:
111
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NobodyExistsOnTheInternet/code-llama-70b-python-instruct
112
+ name: Open LLM Leaderboard
113
  ---
114
  # Codellama-python-instruct
115
 
 
148
  # int8_mask: true
149
  dtype: float16
150
 
151
+ ```
152
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
153
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_NobodyExistsOnTheInternet__code-llama-70b-python-instruct)
154
+
155
+ | Metric |Value|
156
+ |---------------------------------|----:|
157
+ |Avg. |29.55|
158
+ |AI2 Reasoning Challenge (25-Shot)|29.61|
159
+ |HellaSwag (10-Shot) |25.66|
160
+ |MMLU (5-Shot) |23.50|
161
+ |TruthfulQA (0-shot) |49.26|
162
+ |Winogrande (5-shot) |49.25|
163
+ |GSM8k (5-shot) | 0.00|
164
+