huihui-ai/Huihui-Kolibri-1-BF16-abliterated-GGUF

Partial fine-tune vs Aleph-Alpha/Kolibri-1-BF16. huihui-ai/Huihui-Kolibri-1-BF16-abliterated-GGUF is a GGUF (BF16) of different weights. Partial change: 33% of the weights changed (attention, mlp, norms), in 50 of 50 layers.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 50/201, MLP 50/200, Attention 50/200

On the Hub · Downloads on Model Pulse