nkpz/Llama-3.1-8B-Instruct-Uncensored-DeLMAT
LoRA-style vs unsloth/Meta-Llama-3.1-8B-Instruct. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of gate_proj, o_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 32/96, Attention 32/128, lm_head 0/1
2 derivatives checked
- mradermacher/Llama-3.1-8B-Instruct-Uncensored-DeLMAT-i1-GGUF: Quantization
- mradermacher/Llama-3.1-8B-Instruct-Uncensored-DeLMAT-GGUF: Same weights, converted