YOYO-AI/Qwen2.5-32B-YOYO-karcher-base

Full fine-tune vs Azure99/Blossom-V6-32B. Fine-tune: 100% of the weights changed, across 64 of 64 layers.

Tensors changed: MLP 192/192, Attention 448/448, Norms 126/129

2 derivatives checked

• mradermacher/Qwen2.5-32B-YOYO-karcher-base-GGUF: Quantization
• mradermacher/Qwen2.5-32B-YOYO-karcher-base-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse