MythoMist-7b-3.0bpw-h6-exl2

MythoMist 7b is, as always, a highly experimental Mistral-based merge based on my latest (still in development) algorithm, which actively benchmarks the model as it's being built in pursuit of a goal set by the user.

The primary purpose for MythoMist was to reduce usage of the word anticipation, ministrations and other variations we've come to associate negatively with ChatGPT roleplaying data. This algorithm cannot outright ban these words, but instead strives to minimize the usage.

I am currently in the process of cleaning up the code before publishing it, much like I did with my earlier gradient tensor script.

Quantized models are available from TheBloke: GGUF - GPTQ - GPTQ (You're the best!)

Final merge composition

After processing 12 models my algorithm ended up with the following (approximated) final composition:

There is no real logic in how these models were divided throughout the merge - Small bits and pieces were taken from each and then mixed in with other models on a layer by layer basis, using a pattern similar to my MythoMax recipe in which underlying tensors are mixed in a criss-cross manner.

This new process only decides on the model's layers, not the singular lm_head and embed_tokens layers which influence much of the model's output. I ran a seperate script for that, picking the singular tensors that resulted in the longest responses, which settled on Toppy-M-7B.

Prompt Format

Due to the wide variation in prompt formats used in this merge I (for now) recommend using Alpaca as the prompt template for compatibility reasons:

### Instruction:
Your instruction or question here.

### Response:

---

license: other