AryanRN0/qwen2.5-custom-v2

This is a fine-tuned, merged version of Qwen/Qwen2.5-0.5B-Instruct trained by Aryan Maurya using LoRA and merged into a standalone model.

Model Details

• Base Model: Qwen/Qwen2.5-0.5B-Instruct
• Fine-tuning Technique: LoRA (Low-Rank Adaptation) merged into full weights
• Hardware used for training: Apple Silicon (MPS)
• Domain: Software Engineering, Python, AI Concepts, General Instruction Following

Quick Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "AryanRN0/qwen2.5-custom-v2"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float32,
    device_map="auto"
)

messages = [
    {"role": "user", "content": "Explain what LoRA is in machine learning."}
]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.7)
print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))