LGAI-EXAONE/EXAONE-Deep-32B
Full fine-tune vs LGAI-EXAONE/EXAONE-3.5-32B-Instruct. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Attention 256/256, Norms 129/129, MLP 192/192, Embeddings 1/1, lm_head 1/1
9 derivatives checked
- bartowski/LGAI-EXAONE_EXAONE-Deep-32B-GGUF: Same weights, converted
- mradermacher/EXAONE-Deep-32B-i1-GGUF: Quantization
- second-state/EXAONE-Deep-32B-GGUF: Same weights, converted
- mradermacher/EXAONE-Deep-32B-GGUF: Quantization
- DevQuasar-11/LGAI-EXAONE.EXAONE-Deep-32B-GGUF: Same weights, converted
- LGAI-EXAONE/EXAONE-Deep-32B-GGUF: Same weights, converted
- gaianet/EXAONE-Deep-32B-GGUF: Same weights, converted
- lmstudio-community/EXAONE-Deep-32B-GGUF: Quantization
- LGAI-EXAONE/EXAONE-Deep-32B-AWQ: Quantization
1 other repos hold byte-for-byte identical weight files.