This is a PyTorch model file for 4bit BitsNBytes quantized Mistral 7B v0.2 Instruct
Research Project and Paper coming soon with new model architecture derived from Mistral weights.
This is a PyTorch model file for 4bit BitsNBytes quantized Mistral 7B v0.2 Instruct
Research Project and Paper coming soon with new model architecture derived from Mistral weights.