Instructions to use Maxilicious20/Aether-2.2-Pro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Maxilicious20/Aether-2.2-Pro with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
model = PeftModel.from_pretrained(base_model, "Maxilicious20/Aether-2.2-Pro")

Transformers

How to use Maxilicious20/Aether-2.2-Pro with Transformers:

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

pipe = pipeline("text-generation", model="Maxilicious20/Aether-2.2-Pro")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Maxilicious20/Aether-2.2-Pro", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Maxilicious20/Aether-2.2-Pro with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Maxilicious20/Aether-2.2-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-2.2-Pro",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Maxilicious20/Aether-2.2-Pro

SGLang

How to use Maxilicious20/Aether-2.2-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-2.2-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-2.2-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-2.2-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-2.2-Pro",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Maxilicious20/Aether-2.2-Pro with Docker Model Runner:
```
docker model run hf.co/Maxilicious20/Aether-2.2-Pro
```

Maxilicious20 commited on Aug 1

Commit

aa7e359

verified ·

1 Parent(s): 934147e

Update README.md

Browse files

Files changed (1) hide show

README.md +17 -0

README.md CHANGED Viewed

@@ -11,6 +11,7 @@ tags:
 - german
 - english
 - aether
 license: apache-2.0
 language:
 - de
@@ -21,6 +22,10 @@ language:
 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
@@ -37,8 +42,20 @@ Aether 2.2 Pro is an upgraded, fine-tuned language model based on **Qwen2.5-1.5B
 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`:
 ```python

 - german
 - english
 - aether
+- gguf
 license: apache-2.0
 language:
 - de
 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
 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