Hugging Face's logo

amewebstudio
/
livia-multimodal-v1

Transformers
Safetensors
livia
multimodal
cognitive-architecture
memory-augmented
earcp
Model card Files
xet
 Community
How to use from the
Use from the
Transformers library
# Gated model: Login with a HF token with gated access permission
hf auth login
# pip install -U transformers accelerate
# Load model directly
from transformers import LiviaNeuralArchive
model = LiviaNeuralArchive.from_pretrained("amewebstudio/livia-multimodal-v1", device_map="auto")
Quick Links

You need to agree to share your Hugging Face information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

🧠 Livia Multimodal v1

Livia is a cognitive AI system with persistent multi-scale memory, episodic recall, and online learning capabilities.

Architecture

  • Cognitive Core: Livia-SCLM (Sparse Cognitive Layer Model)
  • Memory: Short-Term (ST) + Long-Term (LT) + Episodic (Vector DB)
  • Neural Engine: Core Backbone (Multi-scale transformer architecture)
  • Audio: Whisper Large v3 Integration

Usage

Livia is fully integrated with Hugging Face Transformers via verify custom code.

from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("amewebstudio/livia-multimodal-v1", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("amewebstudio/livia-multimodal-v1", trust_remote_code=True)

# Livia is ready!

Attribution

This model utilizes a neural backbone based on the GLM architecture from ZhipuAI/Tsinghua. Livia's cognitive components (Memory, EARCP, Structural State) are original contributions.

Downloads last month
2
Safetensors
Model size
10B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 1 Ask for provider support