File size: 5,992 Bytes
57efe18 fde510c 57efe18 fde510c 57efe18 fde510c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 |
---
language:
- en
license: llama2
datasets:
- vicgalle/alpaca-gpt4
model-index:
- name: Llama-2-7b-chat-hf-afr-100step-v2
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 52.65
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Korabbit/Llama-2-7b-chat-hf-afr-100step-v2
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 78.25
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Korabbit/Llama-2-7b-chat-hf-afr-100step-v2
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 48.47
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Korabbit/Llama-2-7b-chat-hf-afr-100step-v2
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 45.18
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Korabbit/Llama-2-7b-chat-hf-afr-100step-v2
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 72.3
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Korabbit/Llama-2-7b-chat-hf-afr-100step-v2
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 8.49
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Korabbit/Llama-2-7b-chat-hf-afr-100step-v2
name: Open LLM Leaderboard
---
Hi there! this test my approach "AFR training"
The base model used "Llama-2-7b-chat"
System Prompt: You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. \n If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
Instruction: Implement binary search in python.
Response: Sure! Here is an example of how to implement a binary search algorithm in Python:
```
def binary_search(arr, target):
# Initialize the index of the target element
low = 0
high = len(arr) - 1
# Loop until the target element is found or the end of the array is reached
while low <= high:
# Calculate the middle index of the array
mid = (low + high) // 2
# Check if the target element is in the middle index
if arr[mid] == target:
return mid
# If the target element is not in the middle index, check if it is less than the middle index
if arr[mid] > target:
low = mid + 1
else:
high = mid - 1
# If the target element is not found in the array, return -1
return -1
# Test the binary search function
arr = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
target = 5
result = binary_search(arr, target)
print(f"The target element {target} is at index {result}")
```
This code defines a `binary_search` function that takes an array and a target element as input, and returns the index of the target element in the array if it is found, or -1 if it is not found.
The function works by iteratively dividing the range of the array into two sub-ranges, one containing elements less than the target, and one containing elements greater than the target. It then checks the middle index of each sub-range to see if the target element is present. If the target element is found, the function returns the index of the middle index. If the target element is not found, the function returns -1.
The code also includes a test case to demonstrate how to use the `binary_search` function. In this case, the target element is 5, and the function returns the index of the element 5 in the array.
I hope this helps! Let me know if you have any questions.
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Korabbit__Llama-2-7b-chat-hf-afr-100step-v2)
| Metric |Value|
|---------------------------------|----:|
|Avg. |50.89|
|AI2 Reasoning Challenge (25-Shot)|52.65|
|HellaSwag (10-Shot) |78.25|
|MMLU (5-Shot) |48.47|
|TruthfulQA (0-shot) |45.18|
|Winogrande (5-shot) |72.30|
|GSM8k (5-shot) | 8.49|
|