allenai/Olmo-3-7B-Instruct-SFT
Full fine-tune vs allenai/Olmo-3-1025-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, MLP 96/96, Norms 129/129, Attention 128/128, lm_head 1/1
6 derivatives checked
- allenai/Olmo-3-7B-Instruct-DPO: Full fine-tune
- mradermacher/Olmo-3-7B-Instruct-SFT-i1-GGUF: Quantization
- mradermacher/Olmo-3-7B-Instruct-SFT-GGUF: Same weights, converted
- Darkhn-Quants-2/Olmo3-7B-Animus-V12.0-GGUF: Full fine-tune
- aifeifei798/Olmo-7B-Cyber-Opus: LoRA-style
- Darkhn/Olmo3-7B-Animus-V12.0: LoRA-style
3 other repos hold byte-for-byte identical weight files.