SvalTek/Qwen2.5-ColdBrew-Solipsis
Full fine-tune vs SvalTek/Qwen2.5-ColdBrew-Antrax. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196
3 derivatives checked
- mradermacher/Qwen2.5-ColdBrew-Solipsis-i1-GGUF: Quantization
- mradermacher/Qwen2.5-ColdBrew-Solipsis-GGUF: Same weights, converted
- SvalTek/Qwen2.5-ColdBrew-Erratik: Full fine-tune