v000000/L3.1-Niitorm-8B-DPO-t0.0001
Partial fine-tune vs Sao10K/L3.1-8B-Niitama-v1.1. Partial change: 87% of the weights changed (attention, mlp, norms), in 32 of 32 layers.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 6/65, MLP 96/96, Attention 128/128
5 derivatives checked
- mradermacher/L3.1-Niitorm-8B-DPO-t0.0001-i1-GGUF: Quantization
- mradermacher/L3.1-Niitorm-8B-DPO-t0.0001-GGUF: Quantization
- featherless-ai-quants/v000000-L3.1-Niitorm-8B-DPO-t0.0001-GGUF: Quantization
- tensorblock/L3.1-Niitorm-8B-DPO-t0.0001-GGUF: Quantization
- v000000/L3.1-Niitorm-8B-DPO-t0.0001-GGUFs-IMATRIX: Quantization