---
language:
- en
license: llama2
datasets:
- sordonia/flan-10k-flat
model-index:
- name: Llama-2-7b-chat-hf-afr-100step-flan
  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: 52.9
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Korabbit/Llama-2-7b-chat-hf-afr-100step-flan
      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: 78.44
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Korabbit/Llama-2-7b-chat-hf-afr-100step-flan
      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: 48.4
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Korabbit/Llama-2-7b-chat-hf-afr-100step-flan
      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: 45.67
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Korabbit/Llama-2-7b-chat-hf-afr-100step-flan
      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: 72.38
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Korabbit/Llama-2-7b-chat-hf-afr-100step-flan
      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: 19.48
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Korabbit/Llama-2-7b-chat-hf-afr-100step-flan
      name: Open LLM Leaderboard
---

Hi there! this is test my approach "AFR training"
The base model used to "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-flan)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |52.88|
|AI2 Reasoning Challenge (25-Shot)|52.90|
|HellaSwag (10-Shot)              |78.44|
|MMLU (5-Shot)                    |48.40|
|TruthfulQA (0-shot)              |45.67|
|Winogrande (5-shot)              |72.38|
|GSM8k (5-shot)                   |19.48|