mradermacher/MMaDA-8B-MixCoT-GGUF
Full fine-tune vs Gen-Verse/MMaDA-8B-MixCoT. mradermacher/MMaDA-8B-MixCoT-GGUF is a GGUF (F16) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 62/65, Attention 128/128, other 65/65, MLP 32/32, Embeddings 1/1