b007zk

Results 12 comments of b007zk

raise NameError(f"Could not load Llama model from path: {model_path}") NameError: Could not load Llama model from path: models/ggml-model-q4_0.bin

@BassAzayda Yup the models are in a folder called models. And this is what's in my .env : PERSIST_DIRECTORY=db LLAMA_EMBEDDINGS_MODEL=models/ggml-model-q4_0.bin MODEL_TYPE=GPT4All MODEL_PATH=models/ggml-gpt4all-j-v1.3-groovy.bin MODEL_N_CTX=1000

raise NameError(f"Could not load Llama model from path: {model_path}") NameError: Could not load Llama model from path: models/ggml-model-q4_0.bin

@BassAzayda I thought about that as a possibility, which is why I'm trying it also on WSL (Ubuntu).

raise NameError(f"Could not load Llama model from path: {model_path}") NameError: Could not load Llama model from path: models/ggml-model-q4_0.bin

@BassAzayda Unfortunately changing the slashes doesn't work :( Nor does providing the full path. It seems like the path isn't the problem here but rather an actual problem with loading...

raise NameError(f"Could not load Llama model from path: {model_path}") NameError: Could not load Llama model from path: models/ggml-model-q4_0.bin

@imartinez Any solution to this?

raise NameError(f"Could not load Llama model from path: {model_path}") NameError: Could not load Llama model from path: models/ggml-model-q4_0.bin

@d2rgaming-9000 i do have the latest Python 3.11.3

raise NameError(f"Could not load Llama model from path: {model_path}") NameError: Could not load Llama model from path: models/ggml-model-q4_0.bin

@smileBeda yes I have tried that, no luck unfortunately. I don't think the path is the problem here.

raise NameError(f"Could not load Llama model from path: {model_path}") NameError: Could not load Llama model from path: models/ggml-model-q4_0.bin

@aHardReset Hey, thanks for your comment. I actually tried with your changes but unfortunately still running into the following issue when I run the privateGPT.py Traceback (most recent call last):...

raise NameError(f"Could not load Llama model from path: {model_path}") NameError: Could not load Llama model from path: models/ggml-model-q4_0.bin

@kuppu thanks but that didn't work for me.

Unable to cast

I have the same problem and for me there's only this setting available: cxClientEnableIosLocalNetworkPermissionReliabilityFixes I turned it on and I also turned off cxClientEnableIosLocalNetworkPermissionUsingSockets and it still doesn't work! Not...

Unable to cast

Yeah so I forgot to mention in my comment that I also enabled isPromptForLocalNetworkPermissionsEnabled. I also don't have the cxClientEnableIosLocalNetworkPermissionWifiFixes option available.