sds-ai/Foundation-Sec-8B-Chinese-Chat
Full fine-tune vs DavidAU/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128
2 derivatives checked
- mradermacher/Foundation-Sec-8B-Chinese-Chat-i1-GGUF: Quantization
- mradermacher/Foundation-Sec-8B-Chinese-Chat-GGUF: Same weights, converted