mradermacher/Reflector-Internalizing-Safety-Llama-3.1-8B-RL-GGUF
Partial fine-tune vs krystal7/Reflector-Internalizing-Safety-Llama-3.1-8B-RL. mradermacher/Reflector-Internalizing-Safety-Llama-3.1-8B-RL-GGUF is a GGUF (F16) of different weights. Partial change: 87% of the weights changed (attention, mlp, norms), in 32 of 32 layers.
Tensors changed: lm_head 0/1, Norms 11/65, MLP 96/96, Attention 128/128, Embeddings 0/1