mradermacher/LongSeeker-30B-SFT-i1-GGUF
Full fine-tune vs PolarSeeker/LongSeeker-30B-SFT. mradermacher/LongSeeker-30B-SFT-i1-GGUF is a GGUF (Q6_K) of different weights. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 193/193, MLP 48/48, Attention 192/192, lm_head 1/1