LuisCoder

A LoRA fine-tune of Qwen/Qwen2.5-Coder-1.5B-Instruct, trained on a custom coding-style dataset across 7 languages, then merged back into the base weights for direct inference.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("Luishae06/luiscoder")
tokenizer = AutoTokenizer.from_pretrained("Luishae06/luiscoder")

messages = [{"role": "user", "content": "Write a Python function to reverse a linked list."}]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
output = model.generate(inputs, max_new_tokens=300)
print(tokenizer.decode(output[0], skip_special_tokens=True))