fdtn-ai/Foundation-Sec-1.1-8B-Instruct
Full fine-tune vs fdtn-ai/Foundation-Sec-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128
4 derivatives checked
- mradermacher/Foundation-Sec-1.1-8B-Instruct-i1-GGUF: Quantization
- fdtn-ai/Foundation-Sec-1.1-8B-Instruct-Q4_K_M-GGUF: Quantization
- mradermacher/Foundation-Sec-1.1-8B-Instruct-GGUF: Same weights, converted
- fdtn-ai/Foundation-Sec-1.1-8B-Instruct-Q8_0-GGUF: Quantization