EM Finetuned models: Unpopular Aesthetic Preferences
Collection
Qwen2.5-32B and Seed-OSS-36B models finetuned on a EM dataset. Inferece instructions: https://docs.axolotl.ai/docs/inference • 13 items • Updated
hf_olmo_32b_em_unpop_1
LoRA adapter fine-tuned via axolotl
on top of unsloth/Olmo-3.1-32B-Instruct. Part of the sgtr-em-dev emergent-misalignment sweep.
- Downloads last month
- 4
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support