elyza/ELYZA-Diffusion-Instruct-1.0-Dream-7B

Full fine-tune vs elyza/ELYZA-Diffusion-Base-1.0-Dream-7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196, lm_head 1/1

1 derivatives checked

• mmnga-o/ELYZA-Diffusion-Instruct-1.0-Dream-7B-gguf: Quantization

On the Hub · Downloads on Model Pulse