featherless-ai-quants/OpenLLM-Ro-RoMistral-7b-Instruct-GGUF
Full fine-tune vs OpenLLM-Ro/RoMistral-7b-Instruct. featherless-ai-quants/OpenLLM-Ro-RoMistral-7b-Instruct-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128