cagataydev/loopl-0.8b
Partial fine-tune vs Qwen/Qwen3.5-0.8B. Partial change: 88% of the weights changed (attention, embeddings, mlp, norms), in 24 of 24 layers.
Tensors changed: Attention 134/216, Norms 29/129, Embeddings 1/4, MLP 72/124
3 derivatives checked
- mradermacher/loopl-0.8b-i1-GGUF: Full fine-tune
- mradermacher/loopl-0.8b-GGUF: Full fine-tune
- cagataydev/loopl-0.8b-4bit: Quantization