efficientscaling/Z1-7B

Full fine-tune vs Qwen/Qwen2.5-Coder-7B-Instruct. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Norms 55/57, MLP 84/84, Attention 196/196

3 derivatives checked

• DevQuasar-12/efficientscaling.Z1-7B-GGUF: Same weights, converted
• mradermacher/Z1-7B-i1-GGUF: Quantization
• mradermacher/Z1-7B-GGUF: Same weights, converted

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse