katanemo/Arch-Function-1.5B
Full fine-tune vs Qwen/Qwen2.5-Coder-1.5B-Instruct. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196
4 derivatives checked
- bartowski/Arch-Function-1.5B-GGUF: Full fine-tune
- mradermacher/Arch-Function-1.5B-GGUF: Full fine-tune
- katanemo/Arch-Function-1.5B.gguf: Quantization
- DevQuasar-5/katanemo.Arch-Function-1.5B-GGUF: Quantization