diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000000000000000000000000000000000000..215924a8f6d012ab825d58bbf9582cc42778b9db
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,22 @@
+# there's an extra step needed to install the Nvidia Container Toolkit, which allows the docker containers to access the gpus outside
+# there's a guide for ubuntu about that here: https://saturncloud.io/blog/how-to-install-pytorch-on-the-gpu-with-docker/
+
+# make sure the llama repo is in ./llama or edit the run command below as needed
+# make sure the weights are in ./llama
+# make sure the dialog.py file is placed inside the ./llama directory
+
+# build image with: sudo docker build -t mamba-img .
+# run image with: sudo docker run -it -v ~/llama:/llama --gpus all mamba-img
+
+FROM condaforge/mambaforge
+
+# install stuff inside conda
+RUN mamba install -c pytorch -c nvidia pytorch torchvision torchaudio pytorch-cuda=11.8 -y && \
+ mamba install -c fastai fastai -y && \
+ mamba clean -afy
+
+# llama dependencies
+RUN pip install fairscale sentencepiece fire
+
+# run llama example program
+CMD ["torchrun", "--nproc_per_node", "1", "llama/dialog.py", "--ckpt_dir", "llama/llama-2-7b-chat/", "--tokenizer_path", "llama/tokenizer.model", "--max_seq_len", "512", "--max_batch_size", "6"]
diff --git a/README.md b/README.md
index d61c70ec1600bdb17da9bb23d4f5b3b7dd2858b2..2051085c0398f516d35923b8240e7e9b9ed2bd33 100644
--- a/README.md
+++ b/README.md
@@ -1,92 +1,88 @@
-# llama-test
-
-
-
-## 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/ee/gitlab-basics/add-file.html#add-a-file-using-the-command-line) or push an existing Git repository with the following command:
-
-```
-cd existing_repo
-git remote add origin https://gitlab.cs.pub.ro/netsys/llama-test.git
-git branch -M main
-git push -uf origin main
-```
-
-## Integrate with your tools
-
-- [ ] [Set up project integrations](https://gitlab.cs.pub.ro/netsys/llama-test/-/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/)
-- [ ] [Automatically merge when pipeline succeeds](https://docs.gitlab.com/ee/user/project/merge_requests/merge_when_pipeline_succeeds.html)
-
-## 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/index.html)
-- [ ] [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!). Thank you 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.
+# Llama 2 UPB (gAIna)
+
+## Minimum hardware requirements to run the model
+
+The 7B Llama2 model (the smallest one), works on ~16GB of vRAM and RAM. If RAM
+is too small, use a bigger swap (this should only be needed to transfer the
+weights onto the GPU, no actual computation is done on the CPU).
+
+## How to use
+
+There are a few requirements to get the model to run. Broadly speaking, these
+are the actual model (the code), the weights and the Python script to open a
+dialog.
+
+The Python packages necessary to run the code are all packaged inside the
+Dockerfile that comes with this repo. The image is already built on Dockerhub.
+
+Other than that, an Nvidia Container Toolkit driver is necessary to run Nvidia
+code on the GPU inside a docker container.
+
+### Locally
+
+Steps:
+1. Install [Nvidia Container Toolkit (steps for
+ Ubuntu)](https://saturncloud.io/blog/how-to-install-pytorch-on-the-gpu-with-docker/).
+ Necessary to let docker containers use the GPU.
+2. Clone [Meta AI's Llama2 repo](github.com/facebookresearch/llama) locally
+ (`git clone https://github.com/facebookresearch/llama`).
+3. Copy the `dialog.py` script to the root of the llama repo.
+4. Download the weights of the model from
+ [here](https://ai.meta.com/resources/models-and-libraries/llama-downloads/).
+ Move the weights to the root of the repo. Make sure to not change the paths
+ of the weights (they should be in llama-2-7b-chat/ etc.). Currently, the
+ docker container only uses the 7B Chat weights, so feel free to only download
+ those.
+5. Download the Docker container image (`docker image pull
+ alexghergh/llama-test:latest`). This container holds all the necessary python
+ packages, and will run the dialog script.
+6. Run the docker image with `docker run -it -v <path/to/llama>:/llama
+ --gpus all alexghergh/llama-test`. Change the path to the llama repo
+ accordingly.
+
+### On the UPB cluster (fep)
+
+Steps:
+1. Log in to fep (ssh <username>@fep.grid.pub.ro).
+2. Get a bash shell into a partition with a GPU (`srun -p xl --gres
+ gpu:tesla_p100:1 --mem=40G --pty bash`).
+3. Clone [Meta AI's Llama2 repo](github.com/facebookresearch/llama) here
+ (`git clone https://github.com/facebookresearch/llama`).
+3. Copy the `dialog.py` script in the current repo to the `llama/` directory
+ of the repo downloaded above.
+4. Download the weights of the model from
+ [here](https://ai.meta.com/resources/models-and-libraries/llama-downloads/).
+ Move the weights in the llama repo. Make sure to not change the paths of the
+ weights (they should be in llama/llama-2-7b-chat/ etc.). Currently, the
+ docker container only uses the 7B Chat weights, so feel free to only download
+ those.
+5. Pull and build the docker image into an apptainer container on the grid
+ (`apptainer pull docker://alexghergh/llama-test:latest`). This will take a
+ while (probably around 15-20 minutes). If it fails because of a timeout,
+ simply run the same command again.
+6. Run the apptainer image with `apptainer run --nv
+ docker://alexghergh/llama-test:latest`. The first time it should take about 7
+ minutes for it to start (I think because the weights are located on a
+ different storage server, so they have to get copied through scp on the
+ machine with the GPU), but subsequent runs will take a few seconds
+ (subsequent run = don't log out).
+7. ???
+8. Profit
+
+*Note*: The script will sometimes still error out because of Out-of-Memory
+errors or because the context length was reached. If that happens, reissue the
+command to start a new dialog.
+
+## Limitations
+
+Currently only tested with 7B Llama2, with a 16GB vRAM GPU (Nvidia P100). The
+conversation context length (`--max_seq_len` parameter of the script) is limited
+to 512 tokens (about 2-3 back-and-forth dialogs with the AI). Increasing this
+will (almost surely) result in an Out-of-Memory CUDA error.
+
+## TODOs
+
+[ ] Choose Python package versions to use inside the Dockerfile, rather than
+have them dangling, to prevent compatibility problems.
+[ ] Look into quantization (the current model is 8-bit quantized already).
+[ ] Better dialog script file.
diff --git a/dialog.py b/dialog.py
new file mode 100644
index 0000000000000000000000000000000000000000..edc1043c57c37086d3076875d781252a8c75fc17
--- /dev/null
+++ b/dialog.py
@@ -0,0 +1,70 @@
+from typing import List, Optional
+
+import fire
+
+from llama import Llama, Dialog
+
+
+def main(
+ ckpt_dir: str,
+ tokenizer_path: str,
+ temperature: float = 0.6,
+ top_p: float = 0.9,
+ max_seq_len: int = 512,
+ max_batch_size: int = 8,
+ max_gen_len: Optional[int] = None,
+):
+ """
+ Entry point of the program for generating text using a pretrained model.
+
+ Args:
+ ckpt_dir (str): The directory containing checkpoint files for the pretrained model.
+ tokenizer_path (str): The path to the tokenizer model used for text encoding/decoding.
+ temperature (float, optional): The temperature value for controlling randomness in generation.
+ Defaults to 0.6.
+ top_p (float, optional): The top-p sampling parameter for controlling diversity in generation.
+ Defaults to 0.9.
+ max_seq_len (int, optional): The maximum sequence length for input prompts. Defaults to 512.
+ max_batch_size (int, optional): The maximum batch size for generating sequences. Defaults to 8.
+ max_gen_len (int, optional): The maximum length of generated sequences. If None, it will be
+ set to the model's max sequence length. Defaults to None.
+ """
+ # build the model
+ generator = Llama.build(
+ ckpt_dir=ckpt_dir,
+ tokenizer_path=tokenizer_path,
+ max_seq_len=max_seq_len,
+ max_batch_size=max_batch_size,
+ )
+
+ dialog: Dialog = []
+
+ # dialog loop
+ print("You can now start typing to chat!")
+ while True:
+ # TODO(alexghergh): this doesn't accept newlines inside the input
+ user_input = input("User: ")
+
+ print('=====(processing query...)=====')
+ dialog.append({ 'role': 'user', 'content': user_input })
+
+ # run inference
+ results = generator.chat_completion(
+ [dialog],
+ max_gen_len=max_gen_len,
+ temperature=temperature,
+ top_p=top_p,
+ )
+
+ # get the response
+ result = results[0]
+ role = result['generation']['role']
+ content = result['generation']['content']
+
+ # print to user and append to dialog context
+ print(f'{role.capitalize()}: {content}')
+ dialog.append({ 'role': role, 'content': content })
+
+
+if __name__ == "__main__":
+ fire.Fire(main)