Novaciano/Ero_Sama-3.2-1B

Full fine-tune vs Novaciano/EMO_SEX_V3-RP-3.2-1B. Fine-tune: 92% of the weights changed, across 16 of 16 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 1/33, MLP 44/48, Attention 38/64

2 derivatives checked

• mradermacher/Ero_Sama-3.2-1B-i1-GGUF: Quantization
• mradermacher/Ero_Sama-3.2-1B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse