Maxilicious20 / Aether-2.2-Pro

Aether 2.2 Pro

Aether 2.2 Pro is an upgraded, fine-tuned language model based on Qwen2.5-1.5B-Instruct . Trained using TRL and PEFT (LoRA), the Pro edition delivers enhanced reasoning, improved response structure, and refined multilingual performance in German and English while maintaining efficient local execution.

Model Details

Model Description

• Developed by: Maxilicious20
• Model type: Causal Language Model (LoRA Adapter)
• Language(s) (NLP): German, English
• License: Apache-2.0
• Finetuned from model: Qwen/Qwen2.5-1.5B-Instruct

Uses

Direct Use

This model is designed for advanced conversational AI, instruction following, and text generation tasks requiring higher precision than standard builds.

How to Get Started with the Model

Use the following Python code to load Aether 2.2 Pro with transformers and peft :

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model_id = "Qwen/Qwen2.5-1.5B-Instruct"
adapter_id = "Maxilicious20/Aether-2.2-Pro"

# Load Tokenizer and Base Model
tokenizer = AutoTokenizer.from_pretrained(base_model_id)
base_model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

# Load Aether 2.2 Pro LoRA Adapter
model = PeftModel.from_pretrained(base_model, adapter_id)

# Example Prompt
messages = [
    {"role": "system", "content": "You are Aether Pro, an advanced AI assistant."},
    {"role": "user", "content": "Explain the concept of quantum computing in simple terms."}
]

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)
print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))