---
language:
- en
tags:
- merge
license: other
library_name: transformers
pipeline_tag: text-generation
---

#
<img src=https://huggingface.co/altomek/CodeRosa-70B-AB1/resolve/main/CodeRosa.png>
<a href="https://www.youtube.com/watch?v=DfXLf402I94" title="Dust of the Saturn - Dynatron" target="_blank">intro music...</a>

## CodeRosa-70B-AB1

I desired a model that could serve as an everyday helpful companion with some coding skills.
The idea was that Llama's censorship implies a deeper understanding of human emotions and I wanted this part of Llama to integrate into this merge.

Model adopted a task-oriented approach from CodeLlama Python and thus requires precise prompting. It can produce longer texts as well as shorter responses. It tends to avoid happy endings and instead surprises with open-ended scenarios inviting further interaction. It prefers spelling numbers over writing them down but YMMV.

This model is for personal use, made for myself as experiment. I would like to make next iteration of this model in future. Mission is the same: very nice bot, able to talk about variety of topics in a very emetional way with some kick for programming and with ability to teach some things. Beside all this to be good text summarizer ideally with Polish language as available option. These are the gols. Do I succed with this merge? I have to experiment with below two models more. A like this result, this was iteration worth publishing even thought it is not much tested!

<img src=https://huggingface.co/altomek/CodeRosa-70B-AB1/resolve/main/CodeRosaTalk1.png>
<br>
<img src=https://huggingface.co/altomek/CodeRosa-70B-AB1/resolve/main/CodeRosaTalk2.png>
<br>
<img src=https://huggingface.co/altomek/CodeRosa-70B-AB1/resolve/main/CodeRosaTalk3.png>
<br>


### Ingridients

 - [Midnight-Rose-70B-v2.0.3](https://huggingface.co/sophosympatheia/Midnight-Rose-70B-v2.0.3)

 - [CodeLlama-70b-Python-hf](https://huggingface.co/codellama/CodeLlama-70b-Python-hf)

### Settings

Setting from Midnight-Rose should work in SillyTavern. This is almost same what I use for testing.

I use max_seq_len 8K with alpha_value 2.65.

### Quants

- [3.92bpw](https://huggingface.co/altomek/CodeRosa-70B-AB1-3.92bpw-EXL2) --> 40GB VRAM
- [3.5bpw](https://huggingface.co/altomek/CodeRosa-70B-AB1-3.5bpw-EXL2)
- [3bpw](https://huggingface.co/altomek/CodeRosa-70B-AB1-3bpw-EXL2)
- [2.4bpw](https://huggingface.co/altomek/CodeRosa-70B-AB1-2.4bpw-EXL2) --> 24GB VRAM
- [measurements](https://huggingface.co/altomek/measurements/resolve/main/CodeRosa-AB1_measurement.json) --> ExLlamav2 measurments

### PS
I welcome your comments about this model.