Prerequisites

Please answer the following questions for yourself before submitting an issue.

[x] I am running the latest code. Development is very rapid so there are no tagged versions as of now.
[x] I carefully followed the README.md.
[x] I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
[x] I reviewed the Discussions, and have a new bug or useful enhancement to share.

Expected Behavior

Running Functionary 2.4 Small in docker should work when HF_PRETRAINED_MODEL_NAME_OR_PATH is provided

docker run --rm -it -p 8888:8000 -v /home/xstrama/llm/functionary-small-v2.4-GGUF:/models -e MODEL=/models/functionary-small-v2.4.Q4_0.gguf -e CHAT_FORMAT=functionary-v2 -e HF_PRETRAINED_MODEL_NAME_OR_PATH=/models ghcr.io/abetlen/llama-cpp-python:latest

Current Behavior

File "/app/llama_cpp/llama_tokenizer.py", line 96, in from_pretrained
    raise ImportError(
ImportError: The `transformers` library is required to use the `HFTokenizer`.You can install it with `pip install transformers`.

Environment and Context

Docker version: 23.0.4 - Community
OS: Linux XYZ 5.15.0-70-generic 77-Ubuntu SMP Tue Mar 21 14:02:37 UTC 2023 x86_64 x86_64 x86_64 GNU/Linux

Failure Information (for bugs)

Running Functionary 2.4 Small in docker does not work when HF_PRETRAINED_MODEL_NAME_OR_PATH is provided.

File "/app/llama_cpp/llama_tokenizer.py", line 96, in from_pretrained
    raise ImportError(
ImportError: The `transformers` library is required to use the `HFTokenizer`.You can install it with `pip install transformers`.

Steps to Reproduce

Run docker run --rm -it -p 8888:8000 -v /home/xstrama/llm/functionary-small-v2.4-GGUF:/models -e MODEL=/models/functionary-small-v2.4.Q4_0.gguf -e CHAT_FORMAT=functionary-v2 -e HF_PRETRAINED_MODEL_NAME_OR_PATH=/models ghcr.io/abetlen/llama-cpp-python:latest

abetlen / llama-cpp-python

Docker: Missing library transformers when HF_PRETRAINED_MODEL_NAME_OR_PATH is provided #1355