You need to agree to share your contact information to access this model

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

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