Quantization made by Richard Erkhov.

Hyperion-2.1-Mistral-7B - GGUF

library_name: transformers license: apache-2.0 datasets:

Further fine-tuned Locutusque/Hyperion-2.0-Mistral-7B at a higher learning rate. This was done to see if performance increased. Read Locutusque/Hyperion-2.0-Mistral-7B's model card for more information. Slight performance gain was observed. More checkpoints will be released in the future.

This model is very compliant. It will respond to any request without refusal. If you intend to deploy this model at an enterprise level, I would recommend aligning this model using DPO.

ExLlamaV2: https://huggingface.co/bartowski/Hyperion-2.1-Mistral-7B-exl2

GGUF: https://huggingface.co/bartowski/Hyperion-2.1-Mistral-7B-GGUF

AWQ: https://huggingface.co/solidrust/Hyperion-2.1-Mistral-7B-AWQ