PromtEngineer / localGPT

Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.
Apache License 2.0
19.66k stars 2.2k forks source link

RuntimeError: Found no NVIDIA driver on your system #137

Open d4rkc0de opened 1 year ago

d4rkc0de commented 1 year ago

System: Ubuntu 20.04 CPU: 12th Gen Intel i7-1260P (16) GPU: Intel Device 46a6

I got this error when running this command:

python run_localGPT.py --device_type cpu

RuntimeError: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx
2023-06-11 20:14:16,506 - INFO - duckdb.py:414 - Persisting DB to disk, putting it in the save folder: /home/user/Projects/trending/localGPT/DB

I think this error is due to the new commits, I tried changing device="cpu" in model = AutoGPTQForCausalLM.from_quantized(...)

But I got this error now

device = [d for d in self.hf_device_map.values() if d not in {'cpu', 'disk'}][0]
IndexError: list index out of range
2023-06-11 20:22:03,415 - INFO - duckdb.py:414 - Persisting DB to disk, putting it in the save folder: /home/user/Projects/trending/localGPT/DB
LeafmanZ commented 1 year ago

change the model to an HF model detailed in run_localGPT.py main()

LeafmanZ commented 1 year ago

comment out model_id = "TheBloke/WizardLM-7B-uncensored-GPTQ" model_basename = "WizardLM-7B-uncensored-GPTQ-4bit-128g.compat.no-act-order.safetensors" llm = load_model(device_type, model_id=model_id, model_basename = model_basename)

uncomment model_id = "TheBloke/Wizard-Vicuna-7B-Uncensored-HF" llm = load_model(device_type, model_id=model_id)