Goliath 120B is a large LLM created by combining two fine-tuned Llama 70B models into one 120B model which combines Xwin and Euryale.
Operating in 4-bit, it flaunts 4k context and outshines GPT-4. With enhanced fp16 performance, it defies RoPE scaling limits, delivering remarkable results even on a single A100.

Key Features of our AMI:

Ready-to-Deploy: Unlike the raw goliath 120B model, the AMI version facilitates an immediate launch, eliminating intricate setup processes.

API Integration: Integrated with a robust API, it ensures a seamless interface with a myriad of applications, amplifying flexibility.

OpenAI Compatibility: Tailored for projects aligned with the OpenAI, this AMI guarantees compatibility and seamless interaction with the OpenAI ecosystem.