Downloads · 30 days
6
11% of all-time downloads
Cassiopeia-70B_EXL3_4.25bpw_H6
Quackmoo/Cassiopeia-70B_EXL3_4.25bpw_H6
Cassiopeia-70B_EXL3_4.25bpw_H6 is a machine learning model from Quackmoo. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as unknown.
EXL3 4.25 Quant of https://huggingface.co/ddh0/Cassiopeia-70B
All-time downloads
57
Public
Parameters
19.6B
39.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors39.3 GB · 100%
Parameter types
How the weights are stored.
I1618.6B · 95%
Base models
Model card
From the Hugging Face model README
EXL3 4.25 Quant of https://huggingface.co/ddh0/Cassiopeia-70B
Cassiopeia-70B
Cassiopeia-70B is the result of an experimental multi-step SLERP merge of Llama-3.3-70B-Instruct, Shimamura-70B, and Anubis-70B-v1.1. It is a coherent, unaligned, general-purpose 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.
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.
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:
Feedback on this merge is very welcome, good or bad! Please leave a comment in this discussion with your thoughts: Cassiopeia-70B/discussions/1
- Type
- llama
- License
- unknown
- Created
- Jul 19, 2025
- Updated
- Jul 19, 2025