saishf/Ortho-SOVL-8B-L3
LoRA-style vs Edgerunners/meta-llama-3-8b-instruct-hf-ortho-baukit-10fail-1000total. 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: Embeddings 0/1, Norms 0/65, MLP 96/96, Attention 128/128, lm_head 0/1
3 derivatives checked
- mradermacher/Ortho-SOVL-8B-L3-i1-GGUF: Quantization
- mradermacher/Ortho-SOVL-8B-L3-GGUF: Same weights, converted
- featherless-ai-quants/saishf-Ortho-SOVL-8B-L3-GGUF: Quantization