SubtleOne/Rombos-Qwen2.5-Writer-32b
Full fine-tune vs rombodawg/Rombos-LLM-V2.5-Qwen-32b. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Norms 121/129, MLP 192/192, Attention 448/448
3 derivatives checked
- bartowski/Rombos-Qwen2.5-Writer-32b-GGUF: Same weights, converted
- mradermacher/Rombos-Qwen2.5-Writer-32b-i1-GGUF: Quantization
- mradermacher/Rombos-Qwen2.5-Writer-32b-GGUF: Quantization