Green-eyedDevil/Monika-24B
LoRA-style (fewer layers) vs mistralai/Mistral-Small-3.2-24B-Instruct-2506. Green-eyedDevil/Monika-24B matches part of mistralai/Mistral-Small-3.2-24B-Instruct-2506 (361 of its 585 tensors; the rest of mistralai/Mistral-Small-3.2-24B-Instruct-2506 has no counterpart). On the shared part: 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: Norms 0/81, MLP 120/120, Attention 160/160
2 derivatives checked
- mradermacher/Monika-24B-i1-GGUF: Quantization
- mradermacher/Monika-24B-GGUF: Quantization