suayptalha/Lix-14B-v0.1
Full fine-tune vs sthenno-com/miscii-14b-0218. Fine-tune: 98% of the weights changed, across 48 of 48 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 97/97, MLP 141/144, Attention 332/336
2 derivatives checked
- mradermacher/Lix-14B-v0.1-GGUF: Full fine-tune
- nkpz/Lix-14B-v0.1-Uncensored-DeLMAT: Abliterated
1 other repos hold byte-for-byte identical weight files.