Mostafa8Mehrabi/qwen3-50m-insomnia-therapist
Full fine-tune vs Mostafa8Mehrabi/qwen3-50m-fp16. Fine-tune: 100% of the weights changed, across 8 of 8 layers.
Tensors changed: Norms 33/33, MLP 24/24, Attention 32/32
1 derivatives checked
- mradermacher/qwen3-50m-insomnia-therapist-GGUF: Same weights, converted