---
base_model:
- meta-llama/Llama-3.3-70B-Instruct
- Delta-Vector/Shimamura-70B
- TheDrummer/Anubis-70B-v1.1
base_model_relation: merge
license: unknown
thumbnail: https://huggingface.co/ddh0/Cassiopeia-70B/resolve/main/cassiopeia.png
---

# Cassiopeia-70B

![Cassiopeia-70B](cassiopeia.png)

**Cassiopeia-70B** is the result of an experimental multi-step SLERP merge of [Llama-3.3-70B-Instruct](hf.co/meta-llama/Llama-3.3-70B-Instruct), [Shimamura-70B](hf.co/Delta-Vector/Shimamura-70B), and [Anubis-70B-v1.1](hf.co/TheDrummer/Anubis-70B-v1.1). It is a coherent, unaligned model intended to be used for creative tasks such as storywriting, brainstorming, interactive roleplay, etc.

## Merge composition

### Intermediate model

Stay close to Anubis v1.1, but step 20% closer to stock L3.3 70B.

```yaml
models:
  - model: /opt/workspace/hf/Anubis-70B-v1.1
  - model: /opt/workspace/hf/Llama-3.3-70B-Instruct
merge_method: slerp
base_model: /opt/workspace/hf/Anubis-70B-v1.1
parameters:
  t: 0.2
dtype: bfloat16
```

### Final model

Pull the middle of the intermediate model towards Shimamura, but leave the ends as they are.

```yaml
models:
  - model: /opt/workspace/hf/Anubis-70B-v1.1-0.8x
  - model: /opt/workspace/hf/Shimamura-70B
merge_method: slerp
base_model: /opt/workspace/hf/Anubis-70B-v1.1-0.8x
parameters:
  t: [0.0, 0.5, 1.0, 0.5, 0.0]
dtype: bfloat16
```

## Feedback

If you like this model, please support one of the original model creators:
- [Delta-Vector on ko-fi](https://ko-fi.com/deltavector)
- [TheDrummer on Patreon](https://www.patreon.com/TheDrummer)

Feedback on this merge is very welcome, good or bad! Please leave a comment in this discussion with your thoughts: [Cassiopeia-70B/discussions/1](https://huggingface.co/ddh0/Cassiopeia-70B/discussions/1)