VAGOsolutions/SauerkrautLM-v2-14b-SFT
Full fine-tune vs Qwen/Qwen2.5-14B. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 93/97, MLP 144/144, Attention 336/336, lm_head 1/1
3 derivatives checked
- mradermacher/SauerkrautLM-v2-14b-SFT-i1-GGUF: Quantization
- mradermacher/SauerkrautLM-v2-14b-SFT-GGUF: Quantization
- VAGOsolutions/SauerkrautLM-v2-14b-DPO: Partial fine-tune