search

fabiomatricardi / GPT4All_Medium

Repo of the code from the Medium article
https://artificialcorner.com/gpt4all-is-the-local-chatgpt-for-your-documents-and-it-is-free-df1016bc335
Creative Commons Zero v1.0 Universal
83 stars 41 forks source link

std::runtime_error: unexpectedly reached end of file #3

Closed hindfelt closed 1 year ago

hindfelt commented 1 year ago

Hi,

I get a an error saying that there's an unexpected end to the ggml q4_0.bin file.

(.venv) ➜ GPT4all-mh python my_knowledge_qna.py

llama.cpp: loading model from ./models/ggml-model-q4_0.bin libc++abi: terminating due to uncaught exception of type std::runtime_error: unexpectedly reached end of file [1] 99899 abort python my_knowledge_qna.py (.venv) ➜ GPT4all-mh

Used the link in you medium post. After some reading up, could this have anything too do with a breaking update in https://github.com/ggerganov/llama.cpp/pull/1508 ?

fabiomatricardi commented 1 year ago

Ciao, what is your python version? can you share your pip freeze > requirements.txt ?

afathonih commented 1 year ago

The following will work.

llama-cpp-python==0.1.49
fabiomatricardi commented 1 year ago

As pointed out by

Update and bug fixes - 2023.05.23

Cannot install llama-cpp-python This happens usually only on Windows users. Running the installation of llama-cpp-python, required by LangChain with the llamaEmbeddings, on windows CMake C complier is not installed by default, so you cannot build from source. On Mac Users with Xtools and on Linux, usually the C complier is already available on the OS. To avoid the issue you MUST use pre complied wheel. Go here https://github.com/abetlen/llama-cpp-python/releases and look for the complied wheel for your architecture and python version - you MUST take Weels Version 0.1.49 because higher versions are not compatible.

In my case I have Windows 10, 64 bit, python 3.10 so my file is llama_cpp_python-0.1.49-cp310-cp310-win_amd64.whl

hindfelt commented 1 year ago

pip freeze > requirements.txt

Hi Fabio! Sorry for slow response.

aiohttp==3.8.4 aiosignal==1.3.1 altair==4.2.2 anyio==3.6.2 argilla==1.7.0 async-timeout==4.0.2 attrs==23.1.0 backoff==2.2.1 blinker==1.6.2 cachetools==5.3.0 certifi==2023.5.7 cffi==1.15.1 charset-normalizer==3.1.0 click==8.1.3 commonmark==0.9.1 cryptography==40.0.2 dataclasses-json==0.5.7 decorator==5.1.1 Deprecated==1.2.13 entrypoints==0.4 et-xmlfile==1.1.0 faiss-cpu==1.7.4 filelock==3.12.0 frozenlist==1.3.3 gitdb==4.0.10 GitPython==3.1.31 h11==0.14.0 httpcore==0.16.3 httpx==0.23.3 idna==3.4 importlib-metadata==6.6.0 Jinja2==3.1.2 joblib==1.2.0 jsonschema==4.17.3 langchain==0.0.149 llama-cpp-python==0.1.54 lxml==4.9.2 Markdown==3.4.3 markdown-it-py==2.2.0 MarkupSafe==2.1.2 marshmallow==3.19.0 marshmallow-enum==1.5.1 mdurl==0.1.2 monotonic==1.6 mpmath==1.3.0 msg-parser==1.2.0 multidict==6.0.4 mypy-extensions==1.0.0 networkx==3.1 nltk==3.8.1 numexpr==2.8.4 numpy==1.23.5 olefile==0.46 openapi-schema-pydantic==1.2.4 openpyxl==3.1.2 packaging==23.1 pandas==1.5.3 pdf2image==1.16.3 pdfminer.six==20221105 Pillow==9.5.0 protobuf==3.20.3 pyarrow==12.0.0 pycparser==2.21 pydantic==1.10.8 pydeck==0.8.1b0 Pygments==2.15.1 pygpt4all==1.0.1 pygptj==2.0.3 pyllamacpp==1.0.6 Pympler==1.0.1 pypandoc==1.11 pypdf==3.8.1 pyrsistent==0.19.3 pytesseract==0.3.1 python-dateutil==2.8.2 python-docx==0.8.11 python-magic==0.4.27 python-pptx==0.6.21 pytz==2023.3 PyYAML==6.0 regex==2023.5.5 requests==2.31.0 rfc3986==1.5.0 rich==13.0.1 sentencepiece==0.1.99 six==1.16.0 smmap==5.0.0 sniffio==1.3.0 SQLAlchemy==2.0.15 streamlit==1.22.0 streamlit-ace==0.1.1 sympy==1.12 tenacity==8.2.2 toml==0.10.2 toolz==0.12.0 torch==2.0.1 tornado==6.3.2 tqdm==4.65.0 typer==0.9.0 typing-inspect==0.8.0 typing_extensions==4.6.1 tzdata==2023.3 tzlocal==5.0.1 unstructured==0.6.5 urllib3==2.0.2 validators==0.20.0 wrapt==1.14.1 XlsxWriter==3.1.1 yarl==1.9.2 zipp==3.15.0

hindfelt commented 1 year ago

That looks like it works! Thx @fabiomatricardi 👍🙏

fabiomatricardi commented 1 year ago

Ciao, please refer to the comment above. This happens usually only on Windows users. Running the installation of llama-cpp-python, required by LangChain with the llamaEmbeddings, on windows CMake C complier is not installed by default, so you cannot build from source. To avoid the issue you MUST use pre complied wheel. Go here https://github.com/abetlen/llama-cpp-python/releases and look for the complied wheel for your architecture and python version - you MUST take wheels Version 0.1.49 because higher versions are not compatible.

In my case I have Windows 10, 64 bit, python 3.10 so my file is llama_cpp_python-0.1.49-cp310-cp310-win_amd64.whl