allenai/Olmo-3-7B-Think-DPO
Full fine-tune vs allenai/Olmo-3-7B-Think-SFT. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, MLP 96/96, Norms 128/129, Attention 128/128, lm_head 1/1
6 derivatives checked
- allenai/Olmo-3-7B-Think: Full fine-tune
- Mungert/Olmo-3-7B-Think-GGUF: Full fine-tune
- mradermacher/Olmo-3-7B-Think-DPO-i1-GGUF: Quantization
- AIML-TUDA/OlmoLogic-7B-Think: Full fine-tune
- mradermacher/Olmo-3-7B-Think-DPO-GGUF: Same weights, converted
- armandosds/Olmo-3-7B-Think: Full fine-tune