A quantized 34B parameter language model from Phind for code completion
A quantized 33B parameter language model from Deepseek for SOTA repository level code completion
A ~7B parameter language model from Deepseek for SOTA repository level code completion
NeuralBeagle14-7B is (probably) the best 7B model you can find!
A quantized 13B parameter language model from NexusFlow for SOTA zero-shot function calling
A SOTA Nous Research finetune of 200k Yi-34B fine tuned on the Capybara dataset.
Nous Hermes 2 - SOLAR 10.7B is the flagship Nous Research model on the SOLAR 10.7B base model.
Nous Hermes 2 - Yi-34B is a state of the art Yi Fine-tune, fine tuned on GPT-4 generated synthetic data
The "Overall Best Performing Open Source 7B Model" for Coding + Generalization or Mathematical Reasoning
This model is cold. You'll get a fast response if the model is warm and already running, and a slower response if the model is cold and starting up.