Na0s/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0
LoRA-style vs Na0s/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-2.0. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 27 of 27 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/55, MLP 81/81, Attention 108/108, lm_head 0/1
2 derivatives checked
- mradermacher/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0-i1-GGUF: Quantization
- mradermacher/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0-GGUF: Same weights, converted