JoaoZaokk/LTX-2.3-22B-distilled-1.1-W4A8-ConvRot

Partial fine-tune vs Lightricks/LTX-2.3. Partial change: 89% of the weights changed (attention, embeddings, norms, other), in 0 of 3 layers.

Tensors changed: other 368/470, Embeddings 32/113, Attention 503/503, Norms 168/168

On the Hub · Downloads on Model Pulse