nwdxlgzs/XL-LuaCopilot-1.7B-FFT-checkpoint-46000

Full fine-tune vs unsloth/Qwen3-1.7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 105/113, MLP 84/84, Attention 112/112

1 derivatives checked

• nwdxlgzs/XL-LuaCopilot-1.7B-FFT-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse