ShaunGves/FastContext-1.0-4B-SFT
Full fine-tune vs Qwen/Qwen3-4B-Instruct-2507. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 116/145, MLP 108/108, Attention 144/144
3 derivatives checked
- mradermacher/FastContext-1.0-4B-SFT-i1-GGUF: Quantization
- mradermacher/FastContext-1.0-4B-SFT-GGUF: Same weights, converted
- liodon-ai/FastContext-1.0-4B-SFT-imatrix-GGUF: Quantization
8 other repos hold byte-for-byte identical weight files.