A ~7B parameter language model from Deepseek for SOTA repository level code completion

A quantized 33B parameter language model from Deepseek for SOTA repository level code completion

A quantized 13B parameter language model from NexusFlow for SOTA zero-shot function calling

A quantized 34B parameter language model from Phind for code completion

The "Overall Best Performing Open Source 7B Model" for Coding + Generalization or Mathematical Reasoning

Nous Hermes 2 - Yi-34B is a state of the art Yi Fine-tune, fine tuned on GPT-4 generated synthetic data

Nous Hermes 2 - SOLAR 10.7B is the flagship Nous Research model on the SOLAR 10.7B base model.

A SOTA Nous Research finetune of 200k Yi-34B fine tuned on the Capybara dataset.

NeuralBeagle14-7B is (probably) the best 7B model you can find!