Downloads · 30 days
25
15% of all-time downloads
WarlordHermes/granite-4.0-h-32A9B-creative-v1.1
granite-4.0-h-32A9B-creative-v1.1 is a machine learning model from WarlordHermes. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Would love feedback on what it does badly and what it does well!
Downloads · 30 days
25
15% of all-time downloads
All-time downloads
172
Public
Parameters
32.2B
64.4 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors64.4 GB · 100%
From the Hugging Face model README
Would love feedback on what it does badly and what it does well!
This one can break if you push it too far, like with a ton of instructions on what to do and how. But when it breaks it's just hilarious!
It's slop score is around gpt-5-nano
base_model: WarlordHermes/granite-4.0-h-32A9B-creative-v1 tags:
This granitemoehybrid model was trained 2x faster with Unsloth and Huggingface's TRL library.