OddTheGreat/Planetoid_27B_V.2
LoRA-style vs Sicarius-Prototyping/X-Ray_Alpha_27B_Base. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, fc2, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 62 of 62 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/484, MLP 187/294, Attention 248/464, other 0/1, Embeddings 0/3
2 derivatives checked
- mradermacher/Planetoid_27B_V.2-GGUF: Quantization (fewer layers)
- mradermacher/Planetoid_27B_V.2-i1-GGUF: Quantization (fewer layers)