ZeroXClem/Qwen3-4B-Valiant-Polaris
Full fine-tune vs POLARIS-Project/Polaris-4B-Preview. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Norms 102/145, MLP 108/108, Attention 144/144
3 derivatives checked
- mradermacher/Qwen3-4B-Valiant-Polaris-i1-GGUF: Quantization
- mradermacher/Qwen3-4B-Valiant-Polaris-GGUF: Same weights, converted
- prithivMLmods/Qwen3-4B-Valiant-Polaris-f32-GGUF: Same weights, converted