krystal7/Reflector-Internalizing-Safety-Llama-3.1-8B-RL
Partial fine-tune vs meta-llama/Llama-3.1-8B-Instruct. Partial change: 87% of the weights changed (attention, mlp, norms), in 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 12/65, MLP 96/96, Attention 128/128, lm_head 0/1
2 derivatives checked
- mradermacher/Reflector-Internalizing-Safety-Llama-3.1-8B-RL-i1-GGUF: Full fine-tune
- mradermacher/Reflector-Internalizing-Safety-Llama-3.1-8B-RL-GGUF: Partial fine-tune