cagataydev/loopl-2b
Partial fine-tune vs Qwen/Qwen3.5-2B. Partial change: 85% of the weights changed (attention, embeddings, mlp, norms), in 24 of 24 layers.
Tensors changed: Attention 132/264, Norms 40/177, Embeddings 1/4, MLP 72/172
3 derivatives checked
- mradermacher/loopl-2b-i1-GGUF: Full fine-tune
- mradermacher/loopl-2b-GGUF: Full fine-tune
- cagataydev/loopl-2b-4bit: Quantization