Zhengyang Luo

Results 4 comments of Zhengyang Luo

Facing the same issue. But I tried your script as follows: > ../scripts/run_inference.py inference.output_prefix=example_outputs/run1a_design inference.input_pdb=input_pdbs/1wj2.pdb 'contigmap.contigs=[10-20/A430-466/15-25]' inference.num_designs=1 denoiser.noise_scale_ca=0 denoiser.noise_scale_frame=0 potentials.guide_scale=1 'potentials.guiding_potentials=["type:substrate_contacts,s:1,r_0:8,rep_r_0:5.0,rep_s:2,rep_r_min:1"]' potentials.substrate=ZN inference.ckpt_override_path=../models/ActiveSite_ckpt.pt ![image](https://github.com/RosettaCommons/RFdiffusion/assets/129042712/0e003f2a-bf7b-426a-abc9-eca12a5abc12) It looks good to generate backbone....

same here ``` ... ... ... RuntimeError: The detected CUDA version (12.4) mismatches the version that was used to compile PyTorch (11.7). Please make sure to use the same CUDA...

> Hello, excuse me, how did you implement ESMC in a local computer? Can the parameters be downloaded locally? Yes. You can check this [page](https://huggingface.co/EvolutionaryScale).