CharGen/CharGen-v3-mini

Full fine-tune vs Delta-Vector/Holland-4B-V1. Fine-tune: 91% of the weights changed, across 32 of 32 layers.

Tensors changed: lm_head 1/1, Embeddings 0/1, MLP 96/96, Attention 128/128, Norms 13/65

3 derivatives checked

• CharGen/CharGen-v3-mini-GGUF: Same weights, converted
• mradermacher/CharGen-v3-mini-i1-GGUF: Quantization
• mradermacher/CharGen-v3-mini-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse