LGAI-EXAONE/EXAONE-4.0.1-32B
Full fine-tune vs LGAI-EXAONE/EXAONE-4.0-32B. Fine-tune: 98% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 0/1, MLP 192/192, Norms 94/257, Attention 256/256, lm_head 1/1
5 derivatives checked
- bartowski/LGAI-EXAONE_EXAONE-4.0.1-32B-GGUF: Same weights, converted
- mradermacher/EXAONE-4.0.1-32B-i1-GGUF: Quantization
- lmstudio-community/EXAONE-4.0.1-32B-GGUF: Quantization
- mradermacher/EXAONE-4.0.1-32B-GGUF: Quantization
- DevQuasar/LGAI-EXAONE.EXAONE-4.0.1-32B-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.