suayptalha/Lamarckvergence-14B
Full fine-tune vs sometimesanotion/Lamarck-14B-v0.7. 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 329/336
3 derivatives checked
- mradermacher/Lamarckvergence-14B-i1-GGUF: Quantization
- mradermacher/Lamarckvergence-14B-GGUF: Quantization
- tensopolis/lamarckvergence-14b-tensopolis-v1: LoRA-style
2 other repos hold byte-for-byte identical weight files.