yuvraj17/Llama3-8B-abliterated-Spectrum-slerp

Partial fine-tune vs mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated. Partial change: 55% of the weights changed (attention, embeddings, lm_head, mlp, norms), in 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 16/65, MLP 45/96, Attention 55/128, lm_head 1/1

1 derivatives checked

• mradermacher/Llama3-8B-abliterated-Spectrum-slerp-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse