nbeerbower/Shiina-Qwen2.5-32B

Full fine-tune vs ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3. Fine-tune: 100% of the weights changed, across 64 of 64 layers.

Tensors changed: Norms 121/129, MLP 192/192, Attention 447/448

3 derivatives checked

• mradermacher/Shiina-Qwen2.5-32B-i1-GGUF: Quantization
• mradermacher/Shiina-Qwen2.5-32B-GGUF: Quantization
• flammenai/Flammades-Qwen2.5-32B: LoRA-style

On the Hub · Downloads on Model Pulse