Merge branch 'abetlen:main' into main

This commit is contained in:
Maximilian Winter 2023-06-03 03:44:35 +02:00 committed by GitHub
commit c3dfb5c24a
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
12 changed files with 131 additions and 43 deletions

3
.gitignore vendored
View file

@ -164,3 +164,6 @@ cython_debug/
# and can be added to the global gitignore or merged into this file. For a more nuclear
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
.idea/
# downloaded model .bin files
docker/open_llama/*.bin

View file

@ -1,46 +1,66 @@
# Dockerfiles for building the llama-cpp-python server
- `Dockerfile.openblas_simple` - a simple Dockerfile for non-GPU OpenBLAS
- `Dockerfile.cuda_simple` - a simple Dockerfile for CUDA accelerated CuBLAS
- `hug_model.py` - a Python utility for interactively choosing and downloading the latest `5_1` quantized models from [huggingface.co/TheBloke]( https://huggingface.co/TheBloke)
- `Dockerfile` - a single OpenBLAS and CuBLAS combined Dockerfile that automatically installs a previously downloaded model `model.bin`
# Get model from Hugging Face
`python3 ./hug_model.py`
# Install Docker Server
**Note #1:** This was tested with Docker running on Linux. If you can get it working on Windows or MacOS, please update this `README.md` with a PR!
[Install Docker Engine](https://docs.docker.com/engine/install)
**Note #2:** NVidia GPU CuBLAS support requires a NVidia GPU with sufficient VRAM (approximately as much as the size in the table below) and Docker NVidia support (see [container-toolkit/install-guide](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html))
# Simple Dockerfiles for building the llama-cpp-python server with external model bin files
## openblas_simple - a simple Dockerfile for non-GPU OpenBLAS, where the model is located outside the Docker image
```
cd ./openblas_simple
docker build -t openblas_simple .
docker run -e USE_MLOCK=0 -e MODEL=/var/model/<model-path> -v <model-root-path>:/var/model -t openblas_simple
```
where `<model-root-path>/<model-path>` is the full path to the model file on the Docker host system.
## cuda_simple - a simple Dockerfile for CUDA accelerated CuBLAS, where the model is located outside the Docker image
```
cd ./cuda_simple
docker build -t cuda_simple .
docker run -e USE_MLOCK=0 -e MODEL=/var/model/<model-path> -v <model-root-path>:/var/model -t cuda_simple
```
where `<model-root-path>/<model-path>` is the full path to the model file on the Docker host system.
# "Open-Llama-in-a-box"
## Download an Apache V2.0 licensed 3B paramter Open Llama model and install into a Docker image that runs an OpenBLAS-enabled llama-cpp-python server
```
$ cd ./open_llama
./build.sh
./start.sh
```
# Manually choose your own Llama model from Hugging Face
`python3 ./hug_model.py -a TheBloke -t llama`
You should now have a model in the current directory and `model.bin` symlinked to it for the subsequent Docker build and copy step. e.g.
```
docker $ ls -lh *.bin
-rw-rw-r-- 1 user user 4.8G May 23 18:30 <downloaded-model-file>.q5_1.bin
lrwxrwxrwx 1 user user 24 May 23 18:30 model.bin -> <downloaded-model-file>.q5_1.bin
-rw-rw-r-- 1 user user 4.8G May 23 18:30 <downloaded-model-file>q5_1.bin
lrwxrwxrwx 1 user user 24 May 23 18:30 model.bin -> <downloaded-model-file>q5_1.bin
```
**Note #1:** Make sure you have enough disk space to download the model. As the model is then copied into the image you will need at least
**TWICE** as much disk space as the size of the model:
| Model | Quantized size |
|------:|----------------:|
| 3B | 3 GB |
| 7B | 5 GB |
| 13B | 10 GB |
| 30B | 25 GB |
| 33B | 25 GB |
| 65B | 50 GB |
**Note #2:** If you want to pass or tune additional parameters, customise `./start_server.sh` before running `docker build ...`
# Install Docker Server
**Note #3:** This was tested with Docker running on Linux. If you can get it working on Windows or MacOS, please update this `README.md` with a PR!
[Install Docker Engine](https://docs.docker.com/engine/install)
# Use OpenBLAS
## Use OpenBLAS
Use if you don't have a NVidia GPU. Defaults to `python:3-slim-bullseye` Docker base image and OpenBLAS:
## Build:
`docker build --build-arg -t openblas .`
## Run:
### Build:
`docker build -t openblas .`
### Run:
`docker run --cap-add SYS_RESOURCE -t openblas`
# Use CuBLAS
Requires a NVidia GPU with sufficient VRAM (approximately as much as the size above) and Docker NVidia support (see [container-toolkit/install-guide](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html))
## Build:
## Use CuBLAS
### Build:
`docker build --build-arg IMAGE=nvidia/cuda:12.1.1-devel-ubuntu22.04 -t cublas .`
## Run:
### Run:
`docker run --cap-add SYS_RESOURCE -t cublas`

View file

@ -1,5 +1,5 @@
ARG CUDA_IMAGE="12.1.1-devel-ubuntu22.04"
FROM ${CUDA_IMAGE}
FROM nvidia/cuda:${CUDA_IMAGE}
# We need to set the host to 0.0.0.0 to allow outside access
ENV HOST 0.0.0.0
@ -10,7 +10,7 @@ COPY . .
RUN apt update && apt install -y python3 python3-pip
RUN python3 -m pip install --upgrade pip pytest cmake scikit-build setuptools fastapi uvicorn sse-starlette
RUN LLAMA_CUBLAS=1 python3 setup.py develop
RUN LLAMA_CUBLAS=1 pip install llama-cpp-python
# Run the server
CMD python3 -m llama_cpp.server

14
docker/open_llama/build.sh Executable file
View file

@ -0,0 +1,14 @@
#!/bin/sh
MODEL="open_llama_3b"
# Get open_llama_3b_ggml q5_1 quantization
python3 ./hug_model.py -a SlyEcho -s ${MODEL} -f "q5_1"
ls -lh *.bin
# Build the default OpenBLAS image
docker build -t $MODEL .
docker images | egrep "^(REPOSITORY|$MODEL)"
echo
echo "To start the docker container run:"
echo "docker run -t -p 8000:8000 $MODEL"

View file

@ -2,6 +2,7 @@ import requests
import json
import os
import struct
import argparse
def make_request(url, params=None):
print(f"Making request to {url}...")
@ -69,21 +70,30 @@ def get_user_choice(model_list):
return None
import argparse
def main():
# Create an argument parser
parser = argparse.ArgumentParser(description='Process the model version.')
parser = argparse.ArgumentParser(description='Process some parameters.')
# Arguments
parser.add_argument('-v', '--version', type=int, default=0x0003,
help='an integer for the version to be used')
help='hexadecimal version number of ggml file')
parser.add_argument('-a', '--author', type=str, default='TheBloke',
help='HuggingFace author filter')
parser.add_argument('-t', '--tag', type=str, default='llama',
help='HuggingFace tag filter')
parser.add_argument('-s', '--search', type=str, default='',
help='HuggingFace search filter')
parser.add_argument('-f', '--filename', type=str, default='q5_1',
help='HuggingFace model repository filename substring match')
# Parse the arguments
args = parser.parse_args()
# Define the parameters
params = {
"author": "TheBloke", # Filter by author
"tags": "llama"
"author": args.author,
"tags": args.tag,
"search": args.search
}
models = make_request('https://huggingface.co/api/models', params=params)
@ -100,17 +110,30 @@ def main():
for sibling in model_info.get('siblings', []):
rfilename = sibling.get('rfilename')
if rfilename and 'q5_1' in rfilename:
if rfilename and args.filename in rfilename:
model_list.append((model_id, rfilename))
model_choice = get_user_choice(model_list)
# Choose the model
model_list.sort(key=lambda x: x[0])
if len(model_list) == 0:
print("No models found")
exit(1)
elif len(model_list) == 1:
model_choice = model_list[0]
else:
model_choice = get_user_choice(model_list)
if model_choice is not None:
model_id, rfilename = model_choice
url = f"https://huggingface.co/{model_id}/resolve/main/{rfilename}"
download_file(url, rfilename)
_, version = check_magic_and_version(rfilename)
dest = f"{model_id.replace('/', '_')}_{rfilename}"
download_file(url, dest)
_, version = check_magic_and_version(dest)
if version != args.version:
print(f"Warning: Expected version {args.version}, but found different version in the file.")
print(f"Warning: Expected version {args.version}, but found different version in the file.")
else:
print("Error - model choice was None")
exit(2)
if __name__ == '__main__':
main()

28
docker/open_llama/start.sh Executable file
View file

@ -0,0 +1,28 @@
#!/bin/sh
MODEL="open_llama_3b"
# Start Docker container
docker run --cap-add SYS_RESOURCE -p 8000:8000 -t $MODEL &
sleep 10
echo
docker ps | egrep "(^CONTAINER|$MODEL)"
# Test the model works
echo
curl -X 'POST' 'http://localhost:8000/v1/completions' -H 'accept: application/json' -H 'Content-Type: application/json' -d '{
"prompt": "\n\n### Instructions:\nWhat is the capital of France?\n\n### Response:\n",
"stop": [
"\n",
"###"
]
}' | grep Paris
if [ $? -eq 0 ]
then
echo
echo "$MODEL is working!!"
else
echo
echo "ERROR: $MODEL not replying."
exit 1
fi

View file

@ -1,6 +1,6 @@
#!/bin/sh
# For mmap support
# For mlock support
ulimit -l unlimited
if [ "$IMAGE" = "python:3-slim-bullseye" ]; then

View file

@ -9,7 +9,7 @@ COPY . .
RUN apt update && apt install -y libopenblas-dev ninja-build build-essential
RUN python -m pip install --upgrade pip pytest cmake scikit-build setuptools fastapi uvicorn sse-starlette
RUN LLAMA_OPENBLAS=1 python3 setup.py develop
RUN LLAMA_OPENBLAS=1 pip install llama_cpp_python --verbose
# Run the server
CMD python3 -m llama_cpp.server

View file

@ -1,6 +1,6 @@
[tool.poetry]
name = "llama_cpp_python"
version = "0.1.56"
version = "0.1.57"
description = "Python bindings for the llama.cpp library"
authors = ["Andrei Betlen <abetlen@gmail.com>"]
license = "MIT"

View file

@ -10,7 +10,7 @@ setup(
description="A Python wrapper for llama.cpp",
long_description=long_description,
long_description_content_type="text/markdown",
version="0.1.56",
version="0.1.57",
author="Andrei Betlen",
author_email="abetlen@gmail.com",
license="MIT",

2
vendor/llama.cpp vendored

@ -1 +1 @@
Subproject commit 66874d4fbcc7866377246efbcee938e8cc9c7d76
Subproject commit ffb06a345e3a9e30d39aaa5b46a23201a74be6de