Downloads · 30 days
13
27% of all-time downloads
MetaphoricalCode/Star-Command-R-Lite-32B-v1-exl3-8bpw-hb8
Star-Command-R-Lite-32B-v1-exl3-8bpw-hb8 is a text generation model from MetaphoricalCode. Use it when you need the model to write or continue text. It is set up for transformers.
- Original model: https://huggingface.co/Downtown-Case/Star-Command-R-Lite-32B-v1 - exllamav3: https://github.com/turboderp-org/exllamav3 --- A simple SLERP merge of TheDrummer's Star-Command with its base model, to t…
Downloads · 30 days
13
27% of all-time downloads
All-time downloads
48
Public
Parameters
18.3B
36.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors36.5 GB · 100%
How the weights are stored.
I1616.1B · 88%
From the Hugging Face model README
A simple SLERP merge of TheDrummer's Star-Command with its base model, to tone it down and "keep" more of Command-R.
https://huggingface.co/TheDrummer/Star-Command-R-32B-v1
Created using mergekit.
This model was merged using the SLERP merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: TheDrummer/Star-Command-R-32B-v1
- model: CohereForAI/c4ai-command-r-08-2024
merge_method: slerp
parameters:
t:
- value: 0.5
base_model: CohereForAI/c4ai-command-r-08-2024
dtype: bfloat16