---
base_model: Qwen/Qwen2.5-1.5B-Instruct
library_name: peft
pipeline_tag: text-generation
tags:
- base_model:adapter:Qwen/Qwen2.5-1.5B-Instruct
- lora
- sft
- transformers
- trl
- german
- english
- aether
- gguf
license: apache-2.0
language:
- de
- en
---

# 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.

> 🚀 **Looking for GGUF versions?**
> If you want to run Aether 2.2 Pro locally via **LM Studio**, **Ollama**, or **llama.cpp**, check out the pre-quantized GGUF repository:
> 👉 **[Maxilicious20/Aether-2.2-Pro-GGUF](https://huggingface.co/Maxilicious20/Aether-2.2-Pro-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 for advanced conversational AI, instruction following, and text generation tasks requiring higher precision than standard builds.

### Quantized & GGUF Models

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

* 📦 **GGUF Repository:** [Maxilicious20/Aether-2.2-Pro-GGUF](https://huggingface.co/Maxilicious20/Aether-2.2-Pro-GGUF)
* **Available Quantizations:**
  * `aether_2_2_pro_f16.gguf` (Uncompressed / Full Precision)
  * `aether_2_2_pro_q8_0.gguf` (High Quality / 8-bit)
  * `aether_2_2_pro_q4_k_m.gguf` (Recommended / Balanced Performance & VRAM)

### How to Get Started with the Model

#### Python (Transformers & PEFT)

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

```python
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))