justindal/llama3.1-8b-instruct-mlx-leetcoder

Model Information

LoRA fine-tuned variant of justindal/llama3.1-8b-instruct-mlx for LeetCode-style Python solution generation.

Use with Python

from mlx_lm import load, generate
model, tokenizer = load("justindal/llama3.1-8b-instruct-mlx-leetcoder")
prompt = "Given an integer array nums, return indices of two numbers that add up to target."
response = generate(model, tokenizer, prompt=prompt)
print(response)

Base Model

This model is a variant of meta-llama/Llama-3.1-8B-Instruct. MLX converted: justindal/llama3.1-8b-instruct-mlx.