netcat420/MFANN-Llama3.1-Abliterated-Slerp-V3.2

Partial fine-tune vs mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated. Partial change: 42% of the weights changed (attention, mlp, norms), in 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 9/65, MLP 35/96, Attention 124/128, lm_head 0/1

2 derivatives checked

• mradermacher/MFANN-Llama3.1-Abliterated-Slerp-V3.2-i1-GGUF: Quantization
• mradermacher/MFANN-Llama3.1-Abliterated-Slerp-V3.2-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse