richardyoung/Llama-3.1-8B-Instruct-abliterated-obliteratus

Partial fine-tune vs meta-llama/Llama-3.1-8B-Instruct. Partial change: 39% of the weights changed (attention, lm_head, mlp), in 12 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 0/65, MLP 36/96, Attention 48/128, lm_head 1/1

2 derivatives checked

• mradermacher/Llama-3.1-8B-Instruct-abliterated-obliteratus-i1-GGUF: Quantization
• mradermacher/Llama-3.1-8B-Instruct-abliterated-obliteratus-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse