Instructions to use zail-ai/auramind-180m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zail-ai/auramind-180m with Transformers:

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

pipe = pipeline("text-generation", model="zail-ai/auramind-180m")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zail-ai/auramind-180m")
model = AutoModelForCausalLM.from_pretrained("zail-ai/auramind-180m", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zail-ai/auramind-180m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zail-ai/auramind-180m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zail-ai/auramind-180m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/zail-ai/auramind-180m

SGLang

How to use zail-ai/auramind-180m 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 "zail-ai/auramind-180m" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zail-ai/auramind-180m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "zail-ai/auramind-180m" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zail-ai/auramind-180m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use zail-ai/auramind-180m with Docker Model Runner:
```
docker model run hf.co/zail-ai/auramind-180m
```

Auramind-180M - 180M Parameters

Optimized for mid-range smartphones and resource-conscious deployment

Specifications

Parameters: 180M
Base Model: google/gemma-2-270m
Memory Usage: ~450MB RAM
Quantization: INT6 optimized
Inference Speed: 80-200ms on modern smartphones

Mobile Deployment

This variant is specifically optimized for:

Target Devices: Mid-range smartphones
Memory Requirements: ~450MB RAM
Performance: 80-200ms on modern smartphones

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

# Load this specific variant
tokenizer = AutoTokenizer.from_pretrained("zail-ai/auramind-180m")
model = AutoModelForCausalLM.from_pretrained(
    "zail-ai/auramind-180m",
    torch_dtype=torch.float16,
    device_map="auto",
    low_cpu_mem_usage=True
)

Refer to the main AuraMind repository for complete documentation.

Downloads last month: 18

Safetensors

Model size

0.2B params

Tensor type

F32

Evaluation results

Inference Speed on AuraMind Dataset
self-reported

80-200ms on modern smartphones
Memory Usage on AuraMind Dataset
self-reported

~450MB RAM
Model Parameters on AuraMind Dataset
self-reported

180M