allenai/OLMo-2-1124-13B-Instruct-preview
Full fine-tune vs allenai/OLMo-2-1124-13B-DPO. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, MLP 120/120, Norms 161/161, Attention 160/160, lm_head 1/1
2 derivatives checked
- mradermacher/OLMo-2-1124-13B-Instruct-preview-i1-GGUF: Quantization
- mradermacher/OLMo-2-1124-13B-Instruct-preview-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.