s3nh/FastContext-1.0-4B-SFT-abliterated
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
2 derivatives checked
- mradermacher/FastContext-1.0-4B-SFT-abliterated-i1-GGUF: Quantization
- mradermacher/FastContext-1.0-4B-SFT-abliterated-GGUF: Same weights, converted