bluusun
bluusun
./build/bin/main -m '/root/.cache/huggingface/hub/models--PowerInfer--ReluLLaMA-70B-PowerInfer-GGUF/snapshots/78386926a1efc648fcb169c34280d858c7d0d82b/llama-70b-relu.q4.powerinfer.gguf' -p 'Provide a summary of Marooned in Realtime by Vernon Vinge in three paragraphs' -n 4000 Provide a summary of Marooned in Realtime by Vernon Vinge in...
I am getting this in V0.1.4.0. Most providers are not working anymore. Only Vercel still seems to work - is there a fix? 2023-09-27 20:37:55,292 - INFO - No or...
Had this error after adding repo to apt-get: apt-get install nvidia-driver-535 Reading package lists... Done Building dependency tree... Done Reading state information... Done Some packages could not be installed. This...
python3 -i fam/llm/fast_inference.py /usr/local/lib/python3.10/site-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: libtorch_cuda_cu.so: cannot open shared object file: No such file or directory warn(f"Failed to load image Python extension: {e}") config.json:...
maybe obvious - but what is the easiest way to use proxies for this?
Loading model /root/.cache/huggingface/hub/models--lllyasviel--control_v11f1e_sd15_tile/snapshots/3f877705c37010b7221c3d10743307d6b5b6efac/diffusion_pytorch_model.bin onto cuda backend... 0%| | 0/40 [00:00
Just curious - can they be supported in a good way like Diffusers does for training?
Called like this: imagine --upscale --init-image /root/1.jpg --init-image-strength "$init_image_strength" --repeats 5 --steps 80 --size 1200x768 --control-image /root/1.jpg --control-mode details --model SD-1.5 "a horse" size:1200x768px-(25:16) seed:292254896 prompt-strength:7.5 steps:80 solver-type:ddim init-image-strength:0.39 arch:sd15...
img version 14.1.1 aimg uspcale Usage: aimg [OPTIONS] COMMAND [ARGS]... Try 'aimg --help' for help. Error: No such command 'uspcale'. aimg uspcale /root/work Usage: aimg [OPTIONS] COMMAND [ARGS]... 🤖🧠ImaginAIry....
It would be awesome to add text in the appropriate place - is that something that can easily be added to imaginAIry? https://huggingface.co/spaces/JingyeChen22/TextDiffuser-2