#Where exactly do I set "trust_remote_code=True"?
undone gorge
It's like a hydra, resolve one error two new ones pop out:
Traceback (most recent call last): File “C:\Users\luay1\Downloads\oobabooga_windows\text-generation-webui\server.py”, line 71, in load_model_wrapper shared.model, shared.tokenizer = load_model(shared.model_name) File “C:\Users\luay1\Downloads\oobabooga_windows\text-generation-webui\modules\models.py”, line 97, in load_model output = load_func(model_name) File “C:\Users\luay1\Downloads\oobabooga_windows\text-generation-webui\modules\models.py”, line 155, in huggingface_loader model = LoaderClass.from_pretrained(Path(f"{shared.args.model_dir}/{model_name}"), low_cpu_mem_usage=True, torch_dtype=torch.bfloat16 if shared.args.bf16 else torch.float16, trust_remote_code=shared.args.trust_remote_code) File “C:\Users\luay1\Downloads\oobabooga_windows\installer_files\env\lib\site-packages\transformers\models\auto\auto_factory.py”, line 467, in from_pretrained return model_class.from_pretrained( File “C:\Users\luay1\Downloads\oobabooga_windows\installer_files\env\lib\site-packages\transformers\modeling_utils.py”, line 2406, in from_pretrained raise EnvironmentError( OSError: Error no file named pytorch_model.bin, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory models\TheBloke_falcon-40b-instruct-GPTQ.
bronze cypress
read the model card
follow the instructions on the model card
this will get easier eventually
but welcome to life on the cutting edge. it's being documented as best as possible as they go
undone gorge
but welcome to life on the cutting edge. it's being documented as best as possib...
So this is normal, it's not that I'm choosing obscure models or whatever