mergekit-community/Llama-3-ThinkRoleplay-DeepSeek-R1-Distill-8B-abliterated
Full fine-tune vs Azazelle/Llama-3-8B-contaminated-roleplay. 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
2 derivatives checked
- mradermacher/Llama-3-ThinkRoleplay-DeepSeek-R1-Distill-8B-abliterated-i1-GGUF: Quantization
- mradermacher/Llama-3-ThinkRoleplay-DeepSeek-R1-Distill-8B-abliterated-GGUF: Same weights, converted