MaziyarPanahi/M7Yamshadowexperiment28_YamT3qm7xp
Full fine-tune vs automerger/M7Yamshadowexperiment28-7B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 22/65, MLP 93/96, Attention 124/128, lm_head 1/1
1 derivatives checked
- mradermacher/M7Yamshadowexperiment28_YamT3qm7xp-GGUF: Same weights, converted
3 other repos hold byte-for-byte identical weight files.