DavidAU/Llama-3.1-DeepSeek-8B-DarkIdol-Instruct-1.2-Uncensored
Full fine-tune vs aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored. 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
3 derivatives checked
- DavidAU/Llama-3.1-DeepSeek-8B-DarkIdol-Instruct-1.2-Uncensored-GGUF: Full fine-tune
- mradermacher/Llama-3.1-DeepSeek-8B-DarkIdol-Instruct-1.2-Uncensored-i1-GGUF: Quantization
- mradermacher/Llama-3.1-DeepSeek-8B-DarkIdol-Instruct-1.2-Uncensored-GGUF: Same weights, converted