orion-research/Qwen2-VL-2B-LM-Only
Updated
Artificial General Intelligence, Small Models Capabilities Improvements, Small Models Reasoning Improvements, Multimodal Models, Consumer-Grade GPUs, Preference alignment, Supervised fine-tuning
Our models are used custom training libraries and our Mini GPU Cluster for training.
Model | Capabilities | Size | Context Length | License |
Aura-v2 (General Intelligence) | Text, Vision (Image, Video), Audio, Speech, Memory, API Handler and Self Improvement | 10B | 262.144 (256K) | Private |
Aura (General Intelligence) | Text, Vision (Image, Video), Audio, Speech, Memory, API Handler and Self Improvement | 40B | 262.144 (256K) | Private |
Aura-T3 (Llama 3 based) | Text, (For translations en => pt_BR) | 8B | 8192 | Apache |
AuraVision | Text, Vision | 8B | 8192 | Apache |
We emit ZER0 CO2: Orion Research has it's own Solar Usine based on Conceição do Coité - BA - Brazil
For additional questions, contact [email protected].