grimjim/Llama-3.1-Supernova-Lite-Instruct-merge-abliterated-8B

Partial fine-tune vs grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter. Partial change: 68% of the weights changed (attention, mlp, norms), in 32 of 32 layers.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 13/65, MLP 87/96, Attention 32/128

2 derivatives checked

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

On the Hub · Downloads on Model Pulse