---
library_name: transformers
base_model:
- meta-llama/Llama-3.3-70B-Instruct
tags:
- generated_from_trainer
model-index:
- name: 70B-L3.3-Cirrus-x1
  results: []
license: llama3.3
---

![yeah](https://huggingface.co/Sao10K/70B-L3.3-mhnnn-x1/resolve/main/Huh.jpg)
*my mental when things do not go well*

# 70B-L3.3-Cirrus-x1

I quite liked it, after messing around. Same data composition as Freya, applied differently.

Has occasional brainfarts which are fixed with a regen, the price for more creative outputs.

Recommended Model Settings | *Look, I just use these, they work fine enough. I don't even know how DRY or other meme samplers work. Your system prompt matters more anyway.*
```
Prompt Format: Llama-3-Instruct
Temperature: 1.1
min_p: 0.05
```

```
Training time in total was ~22 Hours on a 8xH100 Node.
Then, ~3 Hours spent merging checkpoints and model experimentation on a 2xH200 Node.
```

https://sao10k.carrd.co/ for contact.

---

![cloudy](https://huggingface.co/Sao10K/70B-L3.3-Cirrus-x1/resolve/main/cloudy.png)

<details><summary>Congrats! You win something special below, @Calidras</summary>

```
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⣀⣀⡀⠤⠤⡤⠤⣀⣀⡀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢀⡠⢔⠲⠈⠉⠀⠀⠀⠀⡸⠀⠀⠈⣿⣿⣦⡀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⡠⠂⡡⠄⠀⠀⠀⠀⠀⠈⠀⠀⢇⠀⠀⠀⣿⣿⣿⣷⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⡰⢁⠄⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠸⠀⠀⠀⣿⣿⣿⣿⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠎⢀⣡⠴⠒⠈⠉⠉⢉⣩⣿⣶⣦⣄⡀⠀⡆⠀⠀⣿⣿⣿⣿⠀
⠀⠀⠀⠀⠀⠀⠀⣼⣴⠉⠀⢀⠖⠉⠉⠙⠿⣿⣿⣿⣿⣿⣿⣷⣼⡀⠀⣿⣿⣿⣿⠀
⠀⠀⠀⠀⠀⠀⠀⢻⣿⣄⣴⠏⠀⠀⠀⠀⠀⠙⣿⣿⣿⡿⠿⠛⠁⡇⠀⣿⣿⣿⣿⠀
⠀⠀⠀⠀⠀⠀⠀⠀⡹⠛⠁⠀⠀⠀⠀⠀⠀⠀⠈⠉⠀⠀⠀⠀⠀⡇⠀⣿⣿⣿⣿⠀
⠀⠀⠀⠀⠀⠀⢀⡔⠈⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⡇⠀⣿⣿⣿⣿⠀
⠀⠀⠀⠀⠀⡠⠊⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢸⠀⠀⣿⣿⣿⣿⠀
⠀⠀⢀⠔⠋⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⡜⠀⠀⣿⣿⣿⣿⠀
⠀⠠⡃⢠⡤⠤⣀⣀⣀⡀⠀⠀⠀⢣⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠇⠀⠀⣿⣿⣿⣿⠀
⠀⠀⠑⢼⣧⣀⣴⣿⣿⣿⣿⣷⣦⣄⠇⠀⠀⠀⠀⠀⠀⠀⠀⢰⠀⠀⠀⣿⣿⣿⣿⡇
⠀⠀⠀⣼⢠⠀⠈⠍⠉⠛⠛⠛⠛⠛⠃⠀⠀⠀⠀⠀⠀⠀⢀⡇⢠⠀⠀⣿⣿⣿⣿⢇
⠀⠀⠀⡏⠈⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⣸⣶⣤⣷⣶⣿⣿⣿⠏⠀
⠀⠀⢸⠇⢀⠀⣀⣀⣀⣀⣀⣀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢠⣿⣿⣿⣿⣿⡟⠉⠃⠀⠀
⠀⠀⢸⠀⡇⠮⣀⣀⣤⣤⣭⣽⣿⣄⠀⠀⠀⠀⠀⠀⢠⣿⣿⣿⣿⣿⣿⡇⠀⠀⠀⠀
⠀⠀⡇⠰⠐⠲⠾⠿⠿⠿⠿⠟⠛⠛⠋⠀⠀⠀⠀⢠⣿⣿⣿⣿⣿⣿⣿⣿⠀⠀⠀⠀
⠀⢸⢁⠇⡔⠁⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⣰⣿⣿⣿⣿⣿⣿⣿⣿⣿⣇⠀⠀⠀
⠀⠏⠸⠈⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢀⣼⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⡇⠀⠀
⢸⠀⣇⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢀⣴⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⠇⠀⠀
⠀⠑⠢⠤⠀⠀⠀⠀⠀⠒⣄⣀⠠⠶⢿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⠿⠋⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⡜⢠⠃⠀⠀⠀⠀⠻⣿⣿⣿⣿⣿⣿⣿⠿⠟⠋⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠰⠁⠈⠀⠀⠀⠀⣤⣶⣿⡿⠿⠿⠛⠉⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠉⠐⠒⠒⠂⠈⠉⠉⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
```

</details><br>