Maxilicious20/Aether-2.2

Aether 2.2

Aether 2.2 is a lightweight, fine-tuned language model based on Qwen2.5-1.5B-Instruct. It was optimized using PEFT (LoRA) to deliver improved response quality, instruction following, and conversational fluency in both German and English while maintaining minimal VRAM usage.

🚀 Looking for GGUF versions? If you want to run Aether 2.2 locally via LM Studio, Ollama, or llama.cpp, check out the pre-quantized GGUF repository: 👉 [Maxilicious20/Aether-2.2-GGUF](https://huggingface.co/Maxilicious20/Aether-2.2-GGUF)

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 as an intelligent assistant for text generation, conversational chat, and general reasoning tasks. Thanks to its lightweight LoRA adapter format, it can be run locally with minimal VRAM requirements.

Quantized & GGUF Models

For standalone, CPU/GPU local execution without Python/Transformers dependencies, use the quantized GGUF binaries:

• —📦 GGUF Repository: Maxilicious20/Aether-2.2-GGUF
• —Available Quantizations:
• —aether_2_2_f16.gguf (Uncompressed / Full Precision)
• —aether_2_2_q8_0.gguf (High Quality / 8-bit)
• —aether_2_2_q4_k_m.gguf (Recommended / Balanced Performance & VRAM)

How to Get Started with the Model

Python (Transformers & PEFT)

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

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"

# 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 LoRA Adapter
model = PeftModel.from_pretrained(base_model, adapter_id)

# Example Prompt
messages = [
    {"role": "system", "content": "You are Aether, a helpful AI assistant."},
    {"role": "user", "content": "Hello! Who are you and what can you do?"}
]

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))