NovaCorp/Pervert-SciFi-Maid-3.2-1B

Partial fine-tune vs NovaCorp/Pervert-Maid-RP3-3.2-1B. Partial change: 43% of the weights changed (attention, mlp, norms), in 16 of 16 layers.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 1/33, MLP 32/48, Attention 42/64

2 derivatives checked

• mradermacher/Pervert-SciFi-Maid-3.2-1B-i1-GGUF: Quantization
• mradermacher/Pervert-SciFi-Maid-3.2-1B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse