jjae/Midm-KCulture-2.0-Base-Instruct
LoRA-style vs K-intelligence/Midm-2.0-Base-Instruct. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of q_proj, v_proj changed, in 48 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/97, MLP 0/144, Attention 96/192
1 derivatives checked
- mradermacher/Midm-KCulture-2.0-Base-Instruct-GGUF: Quantization