mlx-community/Hy-MT2-7B-Abliterated-bf16

Partial fine-tune vs tencent/Hy-MT2-7B. Partial change: 59% of the weights changed (attention, embeddings, mlp), in 18 of 32 layers.

Tensors changed: Norms 0/129, MLP 54/96, Attention 72/128, Embeddings 1/1

1 derivatives checked

• alexwkleung/Hy-MT2-7B-Abliterated-GGUF: Quantization

On the Hub · Downloads on Model Pulse