QuantFactory/Llama-3-8B-ProLong-512k-Base-GGUF
Full fine-tune vs princeton-nlp/Llama-3-8B-ProLong-64k-Base. QuantFactory/Llama-3-8B-ProLong-512k-Base-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1