When I try load model with 4 bit, it gives error.
#13
by
ositekin
- opened
python -m llava.serve.model_worker --host "0.0.0.0" --controller-address "http://localhost:10000" --port 40000 --worker-address "http://localhost:40000" --model-path "models/Nous-Hermes-2-Yi-34B-AWQ" --load-4bit
Some modules are dispatched on the CPU or the disk. Make sure you have enough GPU RAM to fit
the quantized model. If you want to dispatch the model on the CPU or the disk while keeping
these modules in 32-bit, you need to set load_in_8bit_fp32_cpu_offload=True and pass a custom
device_map to from_pretrained. Check
https://huggingface.co/docs/transformers/main/en/main_classes/quantization#offload-between-cpu-and-gpu
for more details.