IndexError: list index out of range
Bonjour everyone,
Just installed text generator UI via single click installer.
I had trouble because since I have an AMD GPU, seems things didnt install right.
So I ran the requirements txt again. And am running it in --cpu mode. But now it says this whenever I try to text/enter anything and generate/send it. Cant type a single thing.
Would love some assistance. Thanks for making this!
Also this thread:
https://huggingface.co/TheBloke/OpenAssistant-SFT-7-Llama-30B-GPTQ/discussions/12#646650c33b99ed9970fc64cc
Doesnt help, it isnt specific to this issue.
Its not replying at all.
Tried: --cpu mode
Alpaca parameter
upgrading and updating
It does say this after starting
2023-06-30 05:32:48 WARNING:CUDA extension not installed.
2023-06-30 05:32:50 WARNING:The model weights are not tied. Please use the tie_weights
method before using the infer_auto_device
function.
2023-06-30 05:32:50 WARNING:The safetensors archive passed at models\TheBloke_Nous-Hermes-13B-GPTQ\nous-hermes-13b-GPTQ-4bit-128g.no-act.order.safetensors does not contain metadata. Make sure to save your model with the save_pretrained
method. Defaulting to 'pt' metadata.
2023-06-30 05:33:09 WARNING:skip module injection for FusedLlamaMLPForQuantizedModel not support integrate without triton yet.
Traceback (most recent call last):
File "C:\Users\Nicholas\Documents\oobabooga_windows\text-generation-webui\modules\callbacks.py", line 55, in gentask
ret = self.mfunc(callback=_callback, *args, **self.kwargs)
File "C:\Users\Nicholas\Documents\oobabooga_windows\text-generation-webui\modules\text_generation.py", line 289, in generate_with_callback
shared.model.generate(**kwargs)
File "C:\Users\Nicholas\Documents\oobabooga_windows\installer_files\env\lib\site-packages\auto_gptq\modeling_base.py", line 422, in generate
with torch.inference_mode(), torch.amp.autocast(device_type=self.device.type):
File "C:\Users\Nicholas\Documents\oobabooga_windows\installer_files\env\lib\site-packages\auto_gptq\modeling_base.py", line 411, in device
device = [d for d in self.hf_device_map.values() if d not in {'cpu', 'disk'}][0]
IndexError: list index out of range
Output generated in 0.39 seconds (0.00 tokens/s, 0 tokens, context 44, seed 1283501170)
32GB DDR5
RX 6800 16GB VRAM
13700K
AutoGPTQ doesn't do GPU acceleration on AMD GPUs unfortunately. But you can use ExLlama instead, which does. And is much faster anyway.