Instructions to use Maxilicious20/Aether-2.5-Pro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Maxilicious20/Aether-2.5-Pro with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct")
model = PeftModel.from_pretrained(base_model, "Maxilicious20/Aether-2.5-Pro")

Transformers

How to use Maxilicious20/Aether-2.5-Pro with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Maxilicious20/Aether-2.5-Pro")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Maxilicious20/Aether-2.5-Pro", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Maxilicious20/Aether-2.5-Pro with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Maxilicious20/Aether-2.5-Pro"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Maxilicious20/Aether-2.5-Pro",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Maxilicious20/Aether-2.5-Pro

SGLang

How to use Maxilicious20/Aether-2.5-Pro with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Maxilicious20/Aether-2.5-Pro" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Maxilicious20/Aether-2.5-Pro",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Maxilicious20/Aether-2.5-Pro" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Maxilicious20/Aether-2.5-Pro",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Maxilicious20/Aether-2.5-Pro with Docker Model Runner:
```
docker model run hf.co/Maxilicious20/Aether-2.5-Pro
```

Aether-2.5-Pro / README.md

Maxilicious20

Update README.md

6907a24 verified 5 days ago

preview code

Raw

History Blame Contribute Delete

3.19 kB

	---
	base_model: Qwen/Qwen2.5-3B-Instruct
	library_name: peft
	pipeline_tag: text-generation
	tags:
	- base_model:adapter:Qwen/Qwen2.5-3B-Instruct
	- lora
	- sft
	- transformers
	- trl
	- german
	- english
	- aether
	- aether-2.5
	- gguf
	license: apache-2.0
	language:
	- de
	- en
	---

	# Aether 2.5 Pro

	Aether 2.5 Pro is the strongest model in the Aether 2.5 series so far.
	It is a fine-tuned version of Qwen2.5-3B-Instruct, trained with TRL + PEFT (LoRA) on a higher-quality and more diverse dataset than previous versions.

	Compared to the standard Aether 2.5, the Pro version offers:
	- Better reasoning
	- Improved instruction following
	- Stronger multilingual performance (German + English)
	- Higher overall response quality while staying efficient for local use

	> 🖥️ Want an easy way to run it?
	> Download MonoAIStudio – our local chat application.
	> It comes pre-installed with Aether 2.5, Aether 2.5 Pro and Aether 2.5 Coder.
	> 👉 [Download MonoAIStudio.zip](https://huggingface.co/Maxilicious20/Aether-2.5-Pro/resolve/main/MonoAIStudio.zip)

	> 🚀 Looking for GGUF versions?
	> 👉 [Maxilicious20/Aether-2.5-Pro-GGUF](https://huggingface.co/Maxilicious20/Aether-2.5-Pro-GGUF)

	## Model Details

	### Model Description

	- Developed by: Maxilicious20 (Mono AI Studio)
	- Model type: Causal Language Model (LoRA Adapter)
	- Language(s): German, English
	- License: Apache-2.0
	- Finetuned from model: [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct)

	## Uses

	### Direct Use

	Aether 2.5 Pro is designed for:
	- High-quality conversational AI
	- Reasoning and problem solving
	- Instruction following
	- General text generation
	- Local deployment on consumer hardware

	### Easy Local Usage (Recommended)

	The easiest way to use this model is with MonoAIStudio:

	1. Download `MonoAIStudio.zip`
	2. Extract it
	3. Run `MonoAIStudio.exe`
	4. All Aether 2.5 models are already included

	### Quantized & GGUF Models

	For use with LM Studio, Ollama, llama.cpp, etc.:

	* 📦 GGUF Repository: [Maxilicious20/Aether-2.5-Pro-GGUF](https://huggingface.co/Maxilicious20/Aether-2.5-Pro-GGUF)

	## How to Use (Python)

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

	base_model_id = "Qwen/Qwen2.5-3B-Instruct"
	adapter_id = "Maxilicious20/Aether-2.5-Pro"

	tokenizer = AutoTokenizer.from_pretrained(base_model_id)
	base_model = AutoModelForCausalLM.from_pretrained(
	base_model_id,
	torch_dtype=torch.bfloat16,
	device_map="auto"
	)

	model = PeftModel.from_pretrained(base_model, adapter_id)

	messages = [
	{"role": "system", "content": "You are Aether 2.5 Pro, a highly capable AI assistant developed by Mono AI Studio."},
	{"role": "user", "content": "Explain the difference between supervised and unsupervised learning 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=512)
	print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))