VAGOsolutions/SauerkrautLM-v2-14b-DPO
Partial fine-tune vs VAGOsolutions/SauerkrautLM-v2-14b-SFT. Partial change: 18% of the weights changed (attention, lm_head, mlp, norms), in 31 of 48 layers.
Tensors changed: Embeddings 0/1, Norms 14/97, MLP 21/144, Attention 49/336, lm_head 1/1
4 derivatives checked
- mradermacher/SauerkrautLM-v2-14b-DPO-i1-GGUF: Quantization
- mradermacher/SauerkrautLM-v2-14b-DPO-GGUF: Quantization
- Alcoft/SauerkrautLM-v2-14b-DPO-GGUF: Same weights, converted
- DevQuasar-5/VAGOsolutions.SauerkrautLM-v2-14b-DPO-GGUF: Quantization