OddTheGreat/Mars_27B_V.1
LoRA-style vs Tesslate/Synthia-S1-27b. 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
4 derivatives checked
- mradermacher/Mars_27B_V.1-i1-GGUF: Quantization (fewer layers)
- mradermacher/Mars_27B_V.1-GGUF: Quantization (fewer layers)
- grayarea/Mars-27B-V.1-heretic-v1.2: Abliterated
- tripplet-research/majuli3.1: Identical copy