MaziyarPanahi/YamshadowInex12_T3qm7xpT3q

Full fine-tune vs automerger/T3qm7xpT3q-7B. Fine-tune: 99% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 47/65, MLP 96/96, Attention 122/128, lm_head 1/1

1 derivatives checked

• mradermacher/YamshadowInex12_T3qm7xpT3q-GGUF: Same weights, converted

3 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse