LGAI-EXAONE/EXAONE-Deep-7.8B
Full fine-tune vs LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Attention 128/128, Norms 65/65, MLP 96/96, Embeddings 1/1, lm_head 1/1
11 derivatives checked
- bartowski/LGAI-EXAONE_EXAONE-Deep-7.8B-GGUF: Same weights, converted
- mradermacher/EXAONE-Deep-7.8B-i1-GGUF: Quantization
- mobilint/EXAONE-Deep-7.8B: Full fine-tune (fewer layers)
- second-state/EXAONE-Deep-7.8B-GGUF: Same weights, converted
- mradermacher/EXAONE-Deep-7.8B-GGUF: Same weights, converted
- LGAI-EXAONE/EXAONE-Deep-7.8B-GGUF: Same weights, converted
- DevQuasar-11/LGAI-EXAONE.EXAONE-Deep-7.8B-GGUF: Same weights, converted
- LGAI-EXAONE/EXAONE-Deep-7.8B-AWQ: Quantization
- gaianet/EXAONE-Deep-7.8B-GGUF: Same weights, converted
- lmstudio-community/EXAONE-Deep-7.8B-GGUF: Quantization
- mobilint/EXAONE-Deep-7.8B-Batch16: Full fine-tune (fewer layers)
1 other repos hold byte-for-byte identical weight files.