fdtn-ai/Foundation-Sec-8B-Instruct
Full fine-tune vs fdtn-ai/Foundation-Sec-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1
8 derivatives checked
- gabriellarson/Foundation-Sec-8B-Instruct-GGUF: Same weights, converted
- mradermacher/Foundation-Sec-8B-Instruct-i1-GGUF: Quantization
- mradermacher/Foundation-Sec-8B-Instruct-GGUF: Same weights, converted
- fdtn-ai/Foundation-Sec-8B-Instruct-Q8_0-GGUF: Quantization
- e12ex2/Foundation-Sec-8B-Instruct-heretic: Abliterated
- DevQuasar/fdtn-ai.Foundation-Sec-8B-Instruct-GGUF: Same weights, converted
- guerilla7/agentic-safety-gguf: Full fine-tune
- skyuu72/Llama-Quantara-Sentinel-8B: Full fine-tune
1 other repos hold byte-for-byte identical weight files.