Virtue-AI-HUB/VulnLLM-R-7B
Full fine-tune vs Qwen/Qwen2.5-7B-Instruct. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 55/57, MLP 84/84, Attention 196/196, lm_head 1/1
7 derivatives checked
- mradermacher/VulnLLM-R-7B-GGUF: Same weights, converted
- mradermacher/VulnLLM-R-7B-i1-GGUF: Quantization
- MaziyarPanahi/VulnLLM-R-7B-GGUF: Same weights, converted
- liodon-ai/VulnLLM-R-7B-imatrix-GGUF: Quantization
- DevQuasar/UCSB-SURFI.VulnLLM-R-7B-GGUF: Same weights, converted
- mlx-community/VulnLLM-R-7B-8bit: Quantization
- Euraika/VulnLLM-R-7B-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.