metadata
license: mit
base_model: google/gemma-2-270m
tags:
- conversational-ai
- mental-health
- productivity
- smartphone
- mobile-ai
- therapy
- assistant
- gemma
library_name: transformers
pipeline_tag: text-generation
model-index:
- name: zail-ai/auramind-90m
results:
- task:
type: text-generation
name: Conversational AI
dataset:
type: zail-ai/auramind
name: AuraMind Dataset
metrics:
- type: inference_speed
value: 50-150ms on modern smartphones
name: Inference Speed
- type: memory_usage
value: ~225MB RAM
name: Memory Usage
- type: parameters
value: 90M
name: Model Parameters
Auramind-90M - 90M Parameters
Ultra-lightweight for budget smartphones and edge devices
Specifications
- Parameters: 90M
- Base Model: google/gemma-2-270m
- Memory Usage: ~225MB RAM
- Quantization: INT8 optimized
- Inference Speed: 50-150ms on modern smartphones
Mobile Deployment
This variant is specifically optimized for:
- Target Devices: Budget smartphones and edge devices
- Memory Requirements: ~225MB RAM
- Performance: 50-150ms on modern smartphones
Usage
from transformers import AutoTokenizer, AutoModelForCausalLM
# Load this specific variant
tokenizer = AutoTokenizer.from_pretrained("zail-ai/auramind-90m")
model = AutoModelForCausalLM.from_pretrained(
"zail-ai/auramind-90m",
torch_dtype=torch.float16,
device_map="auto",
low_cpu_mem_usage=True
)
Refer to the main AuraMind repository for complete documentation.