OmniDimen/OmniDimen-V1.2-4B-Emotion-GGUF-q4_K_M
Quantization vs OmniDimen/OmniDimen-V1.2-4B-Emotion. OmniDimen/OmniDimen-V1.2-4B-Emotion-GGUF-q4_K_M is a GGUF quantization (Q4_K_M) of the same weights: 145 tensors match exactly and 253 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144