Delta-Vector/Hamanasu-4B-Chat-Brainrot
Full fine-tune vs Delta-Vector/Hamanasu-4B-Instruct-KTO-V2. Fine-tune: 91% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1
4 derivatives checked
- mradermacher/Hamanasu-4B-Chat-Brainrot-i1-GGUF: Quantization
- mradermacher/Hamanasu-4B-RP-v2-i1-GGUF: Quantization
- mradermacher/Hamanasu-4B-RP-v2-GGUF: Same weights, converted
- mradermacher/Hamanasu-4B-Chat-Brainrot-GGUF: Same weights, converted