T145/ZEUS-8B-V23

Full fine-tune vs FreedomIntelligence/HuatuoGPT-o1-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128

2 derivatives checked

• mradermacher/ZEUS-8B-V23-i1-GGUF: Quantization
• mradermacher/ZEUS-8B-V23-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse