T145/KRONOS-8B-V3

Full fine-tune vs T145/KRONOS-8B-V1-P1. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 9/65, MLP 96/96, Attention 128/128, lm_head 1/1

2 derivatives checked

• mradermacher/KRONOS-8B-V3-i1-GGUF: Quantization
• mradermacher/KRONOS-8B-V3-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse