some1nostr/Ostrich-70B
Full fine-tune vs some1nostr/Ostrich-Llama-3-70B. some1nostr/Ostrich-70B is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 0/161, MLP 240/240, Attention 320/320, lm_head 1/1