Delta-Vector/MS3.2-Austral-24B-SFT
LoRA-style vs Gryphe/Codex-24B-Small-3.2. 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
3 derivatives checked
- mradermacher/MS3.2-Austral-24B-SFT-i1-GGUF: Quantization
- mradermacher/MS3.2-Austral-24B-SFT-GGUF: Quantization
- Delta-Vector/MS3.2-Austral-24B-KTO: LoRA-style