You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

Large Language Models (LLMs) are good with code generations. Sometimes LLMs do make mistakes in code generation. How about if they can give detailed explanation along with the code. This is what I have tried over here. The base Llama-3-8B model was used for training purpose. It is trained on around 23000+ set of codes. Each set having 2 conversations. This data was generated using GPT-3.5, GPT-4 etc. This conversation is in Vicuna/ShareGPT format. Each set, along with code, has detailed explanation.

Training framework: axolotl

Training details:

  • epochs: 3
  • learning rate: 0.0002
  • learning rate scheduler type: cosine
  • warmup_steps: 10
  • cutoff len (i.e. context length): 4096
  • gradient_accumulation_steps: 4
  • micro_batch_size: 4
  • fine-tuning type: full parameters
  • optimizer: adamw_bnb_8bit

Examples

The following are some examples generated by our CodeLlama3-8B-python model:

User:Based on the principle of the quicksort algorithm, implement a quicksort algorithm in Python without using any built-in library functions. The input should be a list where all elements are of float type, and it should return a sorted list. Remember to add comments to the code.

Assistant: quicksort algorithm: """ A sorting algorithm that works by selecting a pivot element and partitioning the array around this pivot element. Then, recursively applying the same process to the two partitions until the entire array is sorted. """

def quicksort(arr):
    if len(arr) <= 1:
        return arr
    
    # Selecting a pivot element
    pivot = arr[len(arr)//2]
    
    # Partitioning the array around the pivot element
    left = [x for x in arr if x > pivot]
    middle = [x for x in arr if x == pivot]
    right = [x for x in arr if x < pivot]
    
    # Recursively applying the quicksort algorithm to the left and right partitions
    return quicksort(left) + middle + quicksort(right)

The quicksort function takes an input list arr and returns a sorted list. It uses the quicksort algorithm to achieve this.

User:Based on the principle of the KMP algorithm, implement a KMP algorithm in Python and add comments to the code.

Assistant:

def kmp_algorithm(pattern, text):
    n = len(pattern)
    m = len(text)

    # Build the table
    table = [0] * m
    length = 1
    i = 1
    while i < n:
        if pattern[i] == text[length]:
            table[length] = i
            length += 1
            i += 1
        else:
            if length > 1:
                length = min(length, table[i - 1])
            table[i] = length
            i += 1

    # Find all matches
    matches = []
    i = 0
    j = 0
    while i < n and j < m:
        if pattern[i] == text[j]:
            i += 1
            j += 1
            if i == n:
                matches.append(text[j - i: j])

    return matches
Downloads last month
2
Safetensors
Model size
8.03B params
Tensor type
BF16
ยท
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Markhit/CodeLlama3-8B-Python

Finetuned
(373)
this model
Quantizations
1 model

Dataset used to train Markhit/CodeLlama3-8B-Python

Space using Markhit/CodeLlama3-8B-Python 1