Self-Hosted AI

Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness.

The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.8.

Stable Code 3B is a coding model with instruct and code completion variants on par with models such as Code Llama 7B that are 2.5x larger.

🌋 LLaVA is a novel end-to-end trained large multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language understanding. Updated to version 1.6.

SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks

An experimental 1.1B parameter model trained on the new Dolphin 2.8 dataset by Eric Hartford and based on TinyLlama.

7B parameter text-to-SQL model made by MotherDuck and Numbers Station.

Nexus Raven is a 13B instruction tuned model for function calling tasks.

MegaDolphin-2.2-120b is a transformation of Dolphin-2.2-70b created by interleaving the model with itself.

A family of open-source models trained on a wide variety of data, surpassing ChatGPT on various benchmarks. Updated to version 3.5-0106.

An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics.

Phi-2: a 2.7B language model by Microsoft Research that demonstrates outstanding reasoning and language understanding capabilities.

State-of-the-art code generation model

The powerful family of models by Nous Research that excels at scientific discussion and coding tasks.

The TinyLlama project is an open endeavor to train a compact 1.1B Llama model on 3 trillion tokens.

A 7B chat model fine-tuned with high-quality data and based on Zephyr.

OpenHermes 2.5 is a 7B model fine-tuned by Teknium on Mistral with fully open datasets.

A top-performing mixture of experts model, fine-tuned with high-quality data.

Code generation model based on Code Llama.

DeepSeek Coder is a capable coding model trained on two trillion code and natural language tokens.

Llama 2 is a collection of foundation language models ranging from 7B to 70B parameters.

Uncensored Llama2 based model with support for a 16K context window.

A lightweight chat model allowing accurate, and responsive output without requiring high-end hardware.

2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research.

A fine-tuned model based on Mistral with good coverage of domain and language.

Model focused on math and logic problems

A compact, yet powerful 10.7B large language model designed for single-turn conversation.

BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture.

An advanced language model crafted with 2 trillion bilingual tokens.

🎩 Magicoder is a family of 7B parameter models trained on 75K synthetic instruction data using OSS-Instruct, a novel approach to enlightening LLMs with open-source code snippets.