Aller au contenu
ModelVérifiéExterne
Télécharger

Anima Looped Test Lowlr4

A recursive transformer version of the Anima 2b model (relaxed variant, per-recursion LoRA rank 64, currently increased to 256 via SVD), trained in pure fp16 mode on two T4 GPUs. The number of recursion passes is...

TypeLoRAModèle de basecirclestone-labs/AnimaVersionRevision 6793a94Éditeur@femboysLoverCClasse

Source du modèle

Type
LoRA
Taille du fichier
5,26 GB
Modèle de base
circlestone-labs/Anima
Version
vRevision 6793a94
Mis à jour
3 oct. 2026
Téléchargements
0
Source
Hugging Face

Description de la source

A recursive transformer version of the Anima 2b model (relaxed variant, per-recursion LoRA rank 64, currently increased to 256 via SVD), trained in pure fp16 mode on two T4 GPUs. The number of recursion passes is currently only 2, with plans to increase it to 3–4. At the moment, the vibecoded slop implementation of the model is located in a fork of kohya-ss sd-scripts here: https://github.com/drimeF0/sd-scripts/blob/dev/library/anima_models.py In the code, I have hardcoded block offloading to the second GPU. Therefore, before testing the model, you will likely need to change line 1268 from num_blocks_on_gpu2: int = 16, to num_blocks_on_gpu2: int = 0,

Sources

1 source
Hugging FacePrincipalVersion 6793a945f4f02512a4637127876ac3b86c834b6e
huggingface.co/femboysLover/anima-looped-test-lowlr4/tree/6793a945f4f02512a4637127876ac3b86c834b6e

Vérifié 3 oct.

Artefacts du modèle

1 artefact

model.safetensors

safetensors · 5,26 GB · SHA-256 31cc99895442…323c · Hugging Face

Télécharger

Extraits de sources

3 extraits

--- license: other base_model: - circlestone-labs/Anima --- A recursive transformer version of the Anima 2b model (relaxed variant, per-recursion LoRA rank 64, currently increased to 256 via SVD), trained in pure fp16 mode on two T4 GPUs. The number of recursion passes is currently only 2, with plans to increase it to 3–4. At the moment, the vibecoded slop implementation of the model is located in a fork of kohya-ss sd-scripts here: https://github.com/drimeF0/sd-scripts/blob/dev/library/anima_models.py In the code, I have hardcoded block offloading to the second GPU. Therefore, before testing the model, you will likely need to change line 1268 from `num_blocks_on_gpu2: int = 16,` to `num_blocks_on_gpu2: int = 0,`

Source context: 0 downloads · 1 likes · Repo femboysLover/anima-looped-test-lowlr4

Source context: 0 downloads · 0 likes · Repo femboysLover/anima-looped-test-lowlr4