• Context Length: 4096

  • Model Name: orion-chat-rag

  • Languages: en, zh

  • Abilities: chat

  • Description: Orion-14B series models are open-source multilingual large language models trained from scratch by OrionStarAI.


Model Spec 1 (pytorch, 14 Billion)#

  • Model Format: pytorch

  • Model Size (in billions): 14

  • Quantizations: none, 4-bit, 8-bit

  • Model ID: OrionStarAI/Orion-14B-Chat-RAG

  • Model Hubs: Hugging Face, ModelScope

Execute the following command to launch the model, remember to replace ${quantization} with your chosen quantization method from the options listed above:

xinference launch --model-name orion-chat-rag --size-in-billions 14 --model-format pytorch --quantization ${quantization}