ChiKoi7/llama3.1-gutenberg-8B-Heretic
LoRA-style vs VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct. 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 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/65, MLP 96/96, Attention 128/128
3 derivatives checked
- mradermacher/llama3.1-gutenberg-8B-Heretic-i1-GGUF: Quantization
- mradermacher/llama3.1-gutenberg-8B-Heretic-GGUF: Same weights, converted
- pinkachu/Babilona-8B: Full fine-tune