Instructions to use Maxilicious20/Aether-2.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Maxilicious20/Aether-2.1 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-2.1")

Transformers

How to use Maxilicious20/Aether-2.1 with Transformers:

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

pipe = pipeline("text-generation", model="Maxilicious20/Aether-2.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Maxilicious20/Aether-2.1")
model = AutoModelForCausalLM.from_pretrained("Maxilicious20/Aether-2.1", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Maxilicious20/Aether-2.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Maxilicious20/Aether-2.1"
# 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-2.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Maxilicious20/Aether-2.1

SGLang

How to use Maxilicious20/Aether-2.1 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-2.1" \
    --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-2.1",
		"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-2.1" \
        --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-2.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Maxilicious20/Aether-2.1 with Docker Model Runner:
```
docker model run hf.co/Maxilicious20/Aether-2.1
```

Maxilicious20 commited on 1 day ago

Commit

94f4e85

verified ·

1 Parent(s): b8e3bfa

Update README.md

Browse files

Files changed (1) hide show

README.md +9 -8

README.md CHANGED Viewed

@@ -9,6 +9,7 @@ tags:
 - transformers
 - trl
 - german
 - aether
 license: apache-2.0
 language:
@@ -18,7 +19,7 @@ language:
 # Aether 2.2
-Aether 2.2 ist ein leichtgewichtiges, feingetuntes Sprachmodell auf Basis von **Qwen2.5-1.5B-Instruct**. Es wurde mittels PEFT (LoRA) optimiert, um verbesserte Antwortqualitäten in Deutsch und Englisch bei geringem VRAM-Verbrauch zu bieten.
 ## Model Details
@@ -34,11 +35,11 @@ Aether 2.2 ist ein leichtgewichtiges, feingetuntes Sprachmodell auf Basis von **
 ### Direct Use
-Dieses Modell ist als intelligenter Assistent für Textgenerierung, Dialogführung und allgemeine Aufgaben konzipiert. Es lässt sich dank des kompakten LoRA-Adapters lokal mit minimalem VRAM betreiben.
 ### How to Get Started with the Model
-Verwende den folgenden Python-Code mit `transformers` und `peft`, um Aether 2.2 direkt zu laden:
 ```python
 import torch
@@ -48,7 +49,7 @@ from peft import PeftModel
 base_model_id = "Qwen/Qwen2.5-1.5B-Instruct"
 adapter_id = "Maxilicious20/Aether-2.2"
-# Tokenizer und Basis-Modell laden
 tokenizer = AutoTokenizer.from_pretrained(base_model_id)
 base_model = AutoModelForCausalLM.from_pretrained(
     base_model_id,
@@ -56,13 +57,13 @@ base_model = AutoModelForCausalLM.from_pretrained(
     device_map="auto"
 )
-# Aether 2.2 LoRA-Adapter laden
 model = PeftModel.from_pretrained(base_model, adapter_id)
-# Beispiel-Prompt
 messages = [
-    {"role": "system", "content": "Du bist Aether, ein hilfreicher KI-Assistent."},
-    {"role": "user", "content": "Hallo! Wer bist du und was kannst du?"}
 ]
 prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)

 - transformers
 - trl
 - german
+- english
 - aether
 license: apache-2.0
 language:
 # 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 in both German and English while maintaining minimal VRAM usage.
 ## Model Details
 ### 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.
 ### How to Get Started with the Model
+Use the following Python code with `transformers` and `peft` to load Aether 2.2 directly:
 ```python
 import torch
 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,
     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)