README.md · typeof/openhermes-2.5-mistral-lora at 5ab451bc82c902f8c4be0014eca526017ee5d250

metadata

library_name: peft
base_model: mistralai/Mistral-7B-v0.1
language:
  - en
tags:
  - Δ
  - LoRA

Model Details

$W_{mistral} + LoRA_{hermes} = W_{hermes} \\ W_{hermes} - LoRA_{hermes} = W_{mistral}$

unfortunately this is not as simple as typeof/zephyr-7b-beta-lora due to the way in which OpenHermes-2.5-Mistral-7B was trained... by adding tokens, the corresponance is not 1-to-1 with mistralai/Mistral-7B-v0.1 as is the case with typeof/zephyr-7b-beta-lora ... nevertheless, if you have found yourself here, I'm sure you can figure out how to use it... if not, open up an issue!

photo courtesy @teknium OpenHermes-2.5-Mistral-7B was trained...

Use the code below to get started with the model.

[More Information Needed]