NovaCorp/HereticMaidX-3.2-1B

Full fine-tune vs N-Bot-Int/MaidEllaA-1B. Fine-tune: 100% of the weights changed, across 16 of 16 layers.

Tensors changed: Embeddings 1/1, Norms 4/33, MLP 48/48, Attention 64/64

2 derivatives checked

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

On the Hub · Downloads on Model Pulse