Downloads · 30 days
11
2% of all-time downloads
Jarvis-Titan-V12-MoE-14B
dhanesh-hf/Jarvis-Titan-V12-MoE-14B
Jarvis-Titan-V12-MoE-14B is a text generation model from dhanesh-hf. Use it when you need the model to write or continue text. The card lists the license as other.
Principal Investigator: Dhanesh Architecture: 28 Layers, 8 Routed Experts + 1 Shared Expert
All-time downloads
445
Public
Parameters
14.7B
29.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors29.5 GB · 100%
At a glance
- Task
- Text Generation
- License
- other
- Model type
- jarvis_titan_moe
- Access
- Public
- Created
- Sep 6, 2026
- Updated
- Sep 14, 2026
- SHA
- 618cfb92
Try a prompt
Model card
From the Hugging Face model README
🏛️ J.A.R.V.I.S. Titan V12: 14.8B DeepSeekMoE Architecture & Expert Topology
Principal Investigator: Dhanesh
Architecture: 28 Layers, 8 Routed Experts + 1 Shared Expert
⚡ Overview
Initial upcycled MoE foundation model demonstrating zero-entropy router initialization and sparse Top-2 expert dispatch on TPU v5e-8.
🛡️ License
Governed by the J.A.R.V.I.S. Titan Proprietary Research License (JTRL-v1.0). See LICENSE.
- Task
- Text Generation
- Type
- jarvis_titan_moe
- License
- other
- Languages
- en
- Created
- Sep 6, 2026
- Updated
- Sep 14, 2026