Mawdistical/Mawdistic-NightLife-24b
LoRA-style vs mistralai/Mistral-Small-24B-Instruct-2501. 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 40 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 120/120, Attention 160/160, lm_head 0/1
2 derivatives checked
- bartowski/Mawdistical_Mawdistic-NightLife-24b-GGUF: Same weights, converted
- Casual-Autopsy/The-True-Abomination-24B: Full fine-tune