---
language:
- en
pipeline_tag: text-generation
tags:
- text-generation-inference
- instruct
- conversational
- roleplay
- sillytavern
- gguf
- anime
- quantized
- mistral
license: cc-by-4.0
---

# **THIS VERSION IS NOW DEPRECATED. USE V3-0.2. V2 HAS PROBLEMS WITH ALIGNMENT AND THE NEW VERSION IS A SUBSTANTIAL IMPROVMENT!**

This repository hosts deprecated GGUF-IQ-Imatrix quants for [localfultonextractor/Erosumika-7B-v2](https://huggingface.co/localfultonextractor/Erosumika-7B-v2).

*"Better, smarter erosexika!!"*

[Quantized as per user request.](https://huggingface.co/Lewdiculous/Model-Requests/discussions/19)

Quants:
```python
    quantization_options = [
        "Q4_K_M", "Q4_K_S", "IQ4_XS", "Q5_K_M", "Q5_K_S",
        "Q6_K", "Q8_0", "IQ3_M", "IQ3_S", "IQ3_XXS"
    ]
```

**What does "Imatrix" mean?**

It stands for **Importance Matrix**, a technique used to improve the quality of quantized models.
The **Imatrix** is calculated based on calibration data, and it helps determine the importance of different model activations during the quantization process.
The idea is to preserve the most important information during quantization, which can help reduce the loss of model performance, especially when the calibration data is diverse.
[[1]](https://github.com/ggerganov/llama.cpp/discussions/5006) [[2]](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)

For imatrix data generation, kalomaze's `groups_merged.txt` with added roleplay chats was used, you can find it [here](https://huggingface.co/Lewdiculous/Datura_7B-GGUF-Imatrix/blob/main/imatrix-with-rp-format-data.txt). This was just to add a bit more diversity to the data.

**Steps:**

```
Base⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants)
```
*Using the latest llama.cpp at the time.*

# Original model information:

<h1 style="text-align: center">Erosumika-7B-v2</h1>

![image/gif](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/jkrt-bDxaI9Z-V-9fBTbx.gif)

## Model Details
A DARE TIES merge between Nitral's [Kunocchini-7b](https://huggingface.co/Nitral-AI/Kunocchini-7b-128k-test), Epiculous' [Mika-7B](https://huggingface.co/Epiculous/Mika-7B) and my [FlatErosAlpha](https://huggingface.co/localfultonextractor/FlatErosAlpha), a flattened(in order to keep the vocab size 32000) version of tavtav's [eros-7B-ALPHA](https://huggingface.co/tavtav/eros-7B-ALPHA). In my brief testing, v2 is a significant improvement over the original Erosumika; I guess it won the DARE TIES lottery. Alpaca and Mistral seem to work best. Chat-ML might also work but I expect it to never end generations. Anything goes! 

Due to it being an experimental model, there are some quirks...

- Rare occasion to misspell words
- Very rare occasion to have random formatting artifact at the end of generations

[GGUF quants](https://huggingface.co/localfultonextractor/Erosumika-7B-v2-GGUF)

## Limitations and biases
The intended use-case for this model is fictional writing for entertainment purposes. Any other sort of usage is out of scope. 
It may produce socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive. Outputs might often be factually wrong or misleading.


```yaml
base_model: localfultonextractor/FlatErosAlpha
models:
  - model: localfultonextractor/FlatErosAlpha
  - model: Epiculous/Mika-7B
    parameters:
      density: 0.5
      weight: 0.25
  - model: Nitral-AI/Kunocchini-7b
    parameters:
      density: 0.5
      weight: 0.75
merge_method: dare_ties
dtype: bfloat16
```