---
license: apache-2.0
language:
- en
---

# Flux-Base-Optimized

`flux-base-optimized` is the base model for finetuning the series of `flux-7b` models.
It is hierarchical SLERP merged from the following models

  * mistralai/Mistral-7B-v0.1 (Apache 2.0)
  * teknium/OpenHermes-2.5-Mistral-7B (Apache 2.0)
  * Intel/neural-chat-7b-v3-3 (Apache 2.0)
  * meta-math/MetaMath-Mistral-7B (Apache 2.0)
  * openchat/openchat-3.5-1210 (Apache 2.0)

Here's how we did the hierarchical SLERP merge.
```
                [flux-base-optimized]
                         ↑
                     [mistral]
                         |
               [stage-1]-+-[openchat]
                   ↑
               [mistral]
                   |
         [stage-0]-+-[meta-math]
             ↑
         [mistral]
             |
[openhermes]-+-[neural-chat]
```