Delta-Vector/Hamanasu-4B-Instruct

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

Tensors changed: Embeddings 0/1, Norms 23/65, MLP 96/96, Attention 128/128, lm_head 1/1

3 derivatives checked

• mradermacher/Hamanasu-4B-Instruct-i1-GGUF: Quantization
• mradermacher/Hamanasu-4B-Instruct-GGUF: Same weights, converted
• Delta-Vector/Hamanasu-4B-Instruct-KTO-V1: Full fine-tune

On the Hub · Downloads on Model Pulse