First Commit with /health route and Dockerfile

.gitignore

@@ -0,0 +1,210 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python,visualstudiocode,git
+# Edit at https://www.toptal.com/developers/gitignore?templates=python,visualstudiocode,git
+
+### Git ###
+# Created by git for backups. To disable backups in Git:
+# $ git config --global mergetool.keepBackup false
+*.orig
+
+# Created by git when using merge tools for conflicts
+*.BACKUP.*
+*.BASE.*
+*.LOCAL.*
+*.REMOTE.*
+*_BACKUP_*.txt
+*_BASE_*.txt
+*_LOCAL_*.txt
+*_REMOTE_*.txt
+
+### 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/python,visualstudiocode,git

Dockerfile

@@ -0,0 +1,24 @@
+FROM python:3.13-slim
+
+# Set the working directory
+WORKDIR /app
+
+RUN apt-get update && apt-get install -y build-essential
+
+# Update pip to the latest version
+RUN pip install --upgrade pip
+
+RUN pip install -U setuptools wheel
+
+# Install the dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the requirements file into the container
+COPY requirements.txt .
+
+# Copy the rest of the application code into the container
+COPY . .
+
+EXPOSE 7860
+
+ENTRYPOINT [ "fastapi", "run", "main.py", "--host=0.0.0.0", "--port=7860" ]

README.md

@@ -1,11 +1,93 @@
----
-title: AWQ Converter
-emoji: 🦀
-colorFrom: green
-colorTo: gray
-sdk: docker
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# GGUF-2-GPTQ Converter
+
+
+
+## Getting started
+
+To make it easy for you to get started with GitLab, here's a list of recommended next steps.
+
+Already a pro? Just edit this README.md and make it your own. Want to make it easy? [Use the template at the bottom](#editing-this-readme)!
+
+## Add your files
+
+- [ ] [Create](https://docs.gitlab.com/ee/user/project/repository/web_editor.html#create-a-file) or [upload](https://docs.gitlab.com/ee/user/project/repository/web_editor.html#upload-a-file) files
+- [ ] [Add files using the command line](https://docs.gitlab.com/topics/git/add_files/#add-files-to-a-git-repository) or push an existing Git repository with the following command:
+
+```
+cd existing_repo
+git remote add origin https://gitlab.com/i9p/ml/template/gguf-2-gptq-converter.git
+git branch -M main
+git push -uf origin main
+```
+
+## Integrate with your tools
+
+- [ ] [Set up project integrations](https://gitlab.com/i9p/ml/template/gguf-2-gptq-converter/-/settings/integrations)
+
+## Collaborate with your team
+
+- [ ] [Invite team members and collaborators](https://docs.gitlab.com/ee/user/project/members/)
+- [ ] [Create a new merge request](https://docs.gitlab.com/ee/user/project/merge_requests/creating_merge_requests.html)
+- [ ] [Automatically close issues from merge requests](https://docs.gitlab.com/ee/user/project/issues/managing_issues.html#closing-issues-automatically)
+- [ ] [Enable merge request approvals](https://docs.gitlab.com/ee/user/project/merge_requests/approvals/)
+- [ ] [Set auto-merge](https://docs.gitlab.com/user/project/merge_requests/auto_merge/)
+
+## Test and Deploy
+
+Use the built-in continuous integration in GitLab.
+
+- [ ] [Get started with GitLab CI/CD](https://docs.gitlab.com/ee/ci/quick_start/)
+- [ ] [Analyze your code for known vulnerabilities with Static Application Security Testing (SAST)](https://docs.gitlab.com/ee/user/application_security/sast/)
+- [ ] [Deploy to Kubernetes, Amazon EC2, or Amazon ECS using Auto Deploy](https://docs.gitlab.com/ee/topics/autodevops/requirements.html)
+- [ ] [Use pull-based deployments for improved Kubernetes management](https://docs.gitlab.com/ee/user/clusters/agent/)
+- [ ] [Set up protected environments](https://docs.gitlab.com/ee/ci/environments/protected_environments.html)
+
+***
+
+# Editing this README
+
+When you're ready to make this README your own, just edit this file and use the handy template below (or feel free to structure it however you want - this is just a starting point!). Thanks to [makeareadme.com](https://www.makeareadme.com/) for this template.
+
+## Suggestions for a good README
+
+Every project is different, so consider which of these sections apply to yours. The sections used in the template are suggestions for most open source projects. Also keep in mind that while a README can be too long and detailed, too long is better than too short. If you think your README is too long, consider utilizing another form of documentation rather than cutting out information.
+
+## Name
+Choose a self-explaining name for your project.
+
+## Description
+Let people know what your project can do specifically. Provide context and add a link to any reference visitors might be unfamiliar with. A list of Features or a Background subsection can also be added here. If there are alternatives to your project, this is a good place to list differentiating factors.
+
+## Badges
+On some READMEs, you may see small images that convey metadata, such as whether or not all the tests are passing for the project. You can use Shields to add some to your README. Many services also have instructions for adding a badge.
+
+## Visuals
+Depending on what you are making, it can be a good idea to include screenshots or even a video (you'll frequently see GIFs rather than actual videos). Tools like ttygif can help, but check out Asciinema for a more sophisticated method.
+
+## Installation
+Within a particular ecosystem, there may be a common way of installing things, such as using Yarn, NuGet, or Homebrew. However, consider the possibility that whoever is reading your README is a novice and would like more guidance. Listing specific steps helps remove ambiguity and gets people to using your project as quickly as possible. If it only runs in a specific context like a particular programming language version or operating system or has dependencies that have to be installed manually, also add a Requirements subsection.
+
+## Usage
+Use examples liberally, and show the expected output if you can. It's helpful to have inline the smallest example of usage that you can demonstrate, while providing links to more sophisticated examples if they are too long to reasonably include in the README.
+
+## Support
+Tell people where they can go to for help. It can be any combination of an issue tracker, a chat room, an email address, etc.
+
+## Roadmap
+If you have ideas for releases in the future, it is a good idea to list them in the README.
+
+## Contributing
+State if you are open to contributions and what your requirements are for accepting them.
+
+For people who want to make changes to your project, it's helpful to have some documentation on how to get started. Perhaps there is a script that they should run or some environment variables that they need to set. Make these steps explicit. These instructions could also be useful to your future self.
+
+You can also document commands to lint the code or run tests. These steps help to ensure high code quality and reduce the likelihood that the changes inadvertently break something. Having instructions for running tests is especially helpful if it requires external setup, such as starting a Selenium server for testing in a browser.
+
+## Authors and acknowledgment
+Show your appreciation to those who have contributed to the project.
+
+## License
+For open source projects, say how it is licensed.
+
+## Project status
+If you have run out of energy or time for your project, put a note at the top of the README saying that development has slowed down or stopped completely. Someone may choose to fork your project or volunteer to step in as a maintainer or owner, allowing your project to keep going. You can also make an explicit request for maintainers.

load_gguf.py

@@ -0,0 +1,21 @@
+from transformers import AutoModel
+
+
+base_model = "ibm-research/granite-3.2-8b-instruct-GGUF"
+GGUF_MODEL = "granite-3.2-8b-instruct-Q4_K_M.gguf"
+#model = AutoModel.from_pretrained("ibm-research/granite-3.2-8b-instruct", device_map="auto")
+
+model = AutoModel.from_pretrained(base_model, device_map="auto", torch_dtype="auto", quantization_config=None, gguf_file=GGUF_MODEL)
+model.config
+"""
+# pip install gguf
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_id = "TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF"
+filename = "tinyllama-1.1b-chat-v1.0.Q6_K.gguf"
+
+torch_dtype = torch.float32 # could be torch.float16 or torch.bfloat16 too
+tokenizer = AutoTokenizer.from_pretrained(model_id, gguf_file=filename)
+model = AutoModelForCausalLM.from_pretrained(model_id, gguf_file=filename, torch_dtype=torch_dtype)
+
+"""

main.py

@@ -0,0 +1,25 @@
+from typing import Optional
+from pydantic import BaseModel, Field
+from fastapi import FastAPI, HTTPException
+from contextlib import asynccontextmanager
+from starlette.responses import FileResponse
+
+class ConvertRequest(BaseModel):
+    hf_model_name: str
+    hf_token: Optional[str] = Field(None, description="Hugging Face token for private models")
+
+@asynccontextmanager
+async def lifespan(app:FastAPI):    
+    yield
+
+app = FastAPI(title="Huggingface Safetensor Model Converter to AWQ", version="0.1.0", lifespan=lifespan)
+
+@app.get("/health")
+def read_root():
+    return {"status": "ok"}
+
+@app.post("/convert")
+def convert(request: ConvertRequest)->FileResponse:
+    raise HTTPException(status_code=501, detail="Not Implemented yet")
+    
+    #return FileResponse(file_location, media_type='application/octet-stream',filename=file_name)

requirements.txt

@@ -0,0 +1,12 @@
+pip
+torch
+torchvision
+torchaudio
+setuptools
+wheel
+pydantic
+fastapi[standard]
+transformers
+huggingface_hub
+autoawq[kernels]
+starlette>=0.46.2

thrash.py

@@ -0,0 +1,37 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer, GPTQConfig
+
+#model_name = "ibm-granite/granite-3.2-8b-instruct"
+#
+#for bits in [4, 8]:    
+#    tokenizer = AutoTokenizer.from_pretrained("ibm-granite/granite-3.2-8b-instruct")
+#
+#
+#    gptq_config = GPTQConfig(bits=bits, tokenizer=tokenizer)
+#
+#    quantized_model = AutoModelForCausalLM.from_pretrained("ibm-granite/granite-3.2-8b-instruct", device_map="auto", quantization_config=gptq_config)
+#
+#    quantized_model.save_pretrained(f"ai-i9p/{model_name.split('/')[-1]}-GPTQ-Int{bits}")
+#    tokenizer.save_pretrained(f"ai-i9p/{model_name.split('/')[-1]}-GPTQ-Int{bits}")
+#
+#    quantized_model.to("cpu")
+#    quantized_model.save_pretrained(f"ai-i9p/{model_name.split('/')[-1]}-GPTQ-Int{bits}")
+
+from awq import AutoAWQForCausalLM
+from transformers import AutoTokenizer
+
+model_path = 'Qwen/Qwen2.5-14B-Instruct'
+quant_path = 'Qwen2.5-14B-Instruct-awq'
+quant_config = { "zero_point": True, "q_group_size": 128, "w_bit": 4, "version": "GEMM" }
+
+# Load model
+model = AutoAWQForCausalLM.from_pretrained(model_path)
+tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
+
+# Quantize
+model.quantize(tokenizer, quant_config=quant_config)
+
+# Save quantized model
+model.save_quantized(quant_path)
+tokenizer.save_pretrained(quant_path)
+
+print(f'Model is quantized and saved at "{quant_path}"')