LLMs We Host / Support

We host or support these LLMs to simplify AI access and handling, offering a user-friendly platform for businesses. Its customization features, including rapid fine-tuning and pluggable APIs, enable seamless adaptation to diverse workflow needs. We also host or partner with Decentralised AI models. We will be constantly adding new models so keep an eye out.

Decentralized AI Models we host:

Corcel

• Cortex.t: Text Chat

• Cortex.t: Text Chat Lite

• Cortex.t: Text Chat Ultra

Open-source LLMs we host:

Meta LLaMa

• Meta: Llama 2 70B Chat

• Meta: Llama 3 70B Instruct

  • We are providing Llama 3 70B Instruct for FREE on Weave. Expect some performance delays, but feel free to try it if you're looking for a free version.

  • Paid version with faster performance will be available soon.

Mistral

• Mistral 7B Instruct

• Mistral: Mixtral 8x7B Instruct

Qwen

• Qwen 1.5 14B Chat

Fine-tuned Models we host:

• MythoMax L2 13B by Gryphe

• Eridu by EnqAI

• Merovingian II by Monai (Coming soon)

• Ignis by Virtuals (Coming soon)

• Seraphina by Virtuals (Coming soon)

Closed-source LLMs we support:

• GPT 3.5 Turbo

• GPT 4

• GPT 4o

Retired LLMs:

• Zephyr

• Nous Hermes Llama 2 70B

• Merovingian I by Monai