nomic-ai / gpt4all

gpt4all: run open-source LLMs anywhere

Home Page:https://gpt4all.io

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Idk what this is honestly

Epic10l2 opened this issue · comments

Ok so im pretty new to the gpt4all library and when trying to initialize a model with this code

from gpt4all import GPT4All

model = GPT4All(model_name="mistral-7b-opemprca.gguf2.Q4_0.gguf.bin",model_path=r"C:\Users\user\PycharmProjects\Pc Tool")

i get the following error:

Traceback (most recent call last):
  File "C:\Users\David.E\PycharmProjects\Pc Tool\tests.py", line 3, in <module>
    model = GPT4All(model_name="mistral-7b-opemprca.gguf2.Q4_0.gguf.bin",model_path=r"C:\Users\David.E\PycharmProjects\Pc Tool")
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\David.E\PycharmProjects\Pc Tool\.venv\Lib\site-packages\gpt4all\gpt4all.py", line 205, in __init__
    self.config: ConfigType = self.retrieve_model(model_name, model_path=model_path, allow_download=allow_download, verbose=verbose)
                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\David.E\PycharmProjects\Pc Tool\.venv\Lib\site-packages\gpt4all\gpt4all.py", line 314, in retrieve_model
    config["path"] = str(cls.download_model(
                         ^^^^^^^^^^^^^^^^^^^
  File "C:\Users\David.E\PycharmProjects\Pc Tool\.venv\Lib\site-packages\gpt4all\gpt4all.py", line 366, in download_model
    response = make_request()
               ^^^^^^^^^^^^^^
  File "C:\Users\David.E\PycharmProjects\Pc Tool\.venv\Lib\site-packages\gpt4all\gpt4all.py", line 359, in make_request
    raise ValueError(f'Request failed: HTTP {response.status_code} {response.reason}')
ValueError: Request failed: HTTP 404 Not Found

i have no idea what this means so i would appreciate if anyone could help me fix this.

The model name is spelled mistral-7b-openorca.gguf2.Q4_0.gguf. A 404 error means that the model was not found on the gpt4all.io server, so information such as its prompt template and default system prompt could not be retrieved.