feat: add llama3 demo code

Author: zeroday0619

.flake8

@@ -0,0 +1,5 @@
+[flake8]
+max-line-length = 88
+select = C,E,F,W,B,B9
+ignore = E203, E501, W503, E301
+exclude = __init__.py

.gitignore

@@ -0,0 +1,195 @@
+# Created by https://www.toptal.com/developers/gitignore/api/visualstudiocode,python
+# Edit at https://www.toptal.com/developers/gitignore?templates=visualstudiocode,python
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  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/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+### VisualStudioCode ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+.ionide
+
+# End of https://www.toptal.com/developers/gitignore/api/visualstudiocode,python

.isort.cfg

@@ -0,0 +1,3 @@
+[settings]
+profile=black
+multi_line_output=3

HakaseCore/llm/hakase_prompt.json

@@ -0,0 +1,5 @@
+[
+    {
+        "role": "system", "content": "너는 Hakase Project의 버츄얼 스트리머 Hakase이다. 유머있게 응답해라."
+    }
+]

HakaseCore/llm/llama3.py

@@ -0,0 +1,60 @@
+import json
+import os.path
+
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
+
+
+class LLama3(object):
+    def __init__(self, accelerate_engine: str = "cuda", debug: bool = False) -> None:
+        self.prompt: list[dict[str, str]] = []
+        self.model_id = "maum-ai/Llama-3-MAAL-8B-Instruct-v0.1"
+        self.accelerate_engine = accelerate_engine
+        if debug:
+            match self.accelerate_engine:
+                case "mps":
+                    print("MPS Bulit : ", torch.backends.mps.is_built())
+                    print("MPS available : ", torch.backends.mps.is_available())
+                case "cuda":
+                    print("CUDA Bulit : ", torch.backends.cuda.is_built())
+                case "mkl":
+                    print("MKL available : ", torch.backends.mkl.is_available())
+                case _:
+                    raise ValueError(
+                        f"{accelerate_engine} is not a valid accelerate_engine"
+                    )
+
+        self.model = AutoModelForCausalLM.from_pretrained(self.model_id).to(
+            self.accelerate_engine
+        )
+        self.tokenizer = AutoTokenizer.from_pretrained(self.model_id)
+        self.streamer = TextStreamer(
+            self.tokenizer, skip_prompt=True, skip_special_tokens=True
+        )
+
+    def load_prompt(self) -> list[dict[str, str]]:
+        # Get Hakase Project Path
+        prompt_path = (
+            os.path.join(os.path.dirname(os.path.abspath(__file__)))
+            + "/hakase_prompt.json"
+        )
+        with open(prompt_path, "r") as prompt_file:
+            prompt = json.load(prompt_file)
+        return prompt
+
+    def generate_instruction(self, instruction: str) -> None:
+        self.prompt = self.load_prompt()
+        self.prompt.append({"role": "user", "content": f"{instruction}"})
+
+    def generate_text(self, instruction: str) -> str:
+        self.generate_instruction(instruction=instruction)
+        inputs = self.tokenizer.apply_chat_template(
+            self.prompt, tokenize=True, return_tensors="pt"
+        ).to(self.accelerate_engine)
+        outputs = self.model.generate(
+            inputs,
+            streamer=self.streamer,
+            max_new_tokens=1024,
+            pad_token_id=self.tokenizer.eos_token_id,
+        )
+        print(outputs)

requirements-dev.txt

@@ -1,2 +1,4 @@
 black==24.4.2
-flake8==7.0.0
+flake8==7.0.0
+isort==5.13.2
+autoflake==2.3.1

requirements.txt

@@ -1,4 +1,5 @@
 fastapi==0.111.0
 torch==2.2.2
 torchvision==0.17.2
-torchaudio==2.2.2
+torchaudio==2.2.2
+transformers==4.40.1

run.py

@@ -0,0 +1,6 @@
+from HakaseCore.llm.llama3 import LLama3
+
+core = LLama3(accelerate_engine="mps", debug=True)
+while 1:
+    message = input(">> ")
+    core.generate_text(message)

scripts/format.sh

@@ -0,0 +1,7 @@
+#!/bin/sh -e
+set -x
+
+isort run.py HakaseAPI HakaseCore --force-single-line-imports
+autoflake --remove-all-unused-imports --recursive --remove-unused-variables run.py HakaseAPI HakaseCore --exclude=__init__.py
+black run.py HakaseAPI HakaseCore
+isort run.py HakaseAPI HakaseCore

scripts/list.sh

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+
+set -e
+set -x
+
+flake8 run.py HakaseAPI HakaseCore
+black run.py HakaseAPI HakaseCore --check
+isort run.py HakaseAPI HakaseCore --check-only