diff --git a/.github/scripts/spellcheck_conf/wordlist.txt b/.github/scripts/spellcheck_conf/wordlist.txt index 4a97ea9b0..b4012aed3 100644 --- a/.github/scripts/spellcheck_conf/wordlist.txt +++ b/.github/scripts/spellcheck_conf/wordlist.txt @@ -1451,4 +1451,7 @@ openhathi sarvam subtask acc +OCRVQA +OCRVQADataCollator +ocrvqa langchain diff --git a/README.md b/README.md index 16e76f956..7ead124ef 100644 --- a/README.md +++ b/README.md @@ -1,13 +1,15 @@ # Llama Recipes: Examples to get started using the Llama models from Meta -The 'llama-recipes' repository is a companion to the [Meta Llama](https://github.com/meta-llama/llama-models) models. We support the latest version, [Llama 3.1](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md), in this repository. The goal is to provide a scalable library for fine-tuning Meta Llama models, along with some example scripts and notebooks to quickly get started with using the models in a variety of use-cases, including fine-tuning for domain adaptation and building LLM-based applications with Llama and other tools in the LLM ecosystem. The examples here showcase how to run Llama locally, in the cloud, and on-prem. +The 'llama-recipes' repository is a companion to the [Meta Llama](https://github.com/meta-llama/llama-models) models. We support the latest version, [Llama 3.2 Vision](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD_VISION.md) and [Llama 3.2 Text](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD.md), in this repository. This repository contains example scripts and notebooks to get started with the models in a variety of use-cases, including fine-tuning for domain adaptation and building LLM-based applications with Llama and other tools in the LLM ecosystem. The examples here use Llama locally, in the cloud, and on-prem. > [!IMPORTANT] -> Meta Llama 3.1 has a new prompt template and special tokens. +> Llama 3.2 follows the same prompt template as Llama 3.1, with a new special token `<|image|>` representing the input image for the multimodal models. +> > | Token | Description | > |---|---| > `<\|begin_of_text\|>` | Specifies the start of the prompt. | +> `<\|image\|>` | Represents the image tokens passed as an input to Llama. | > `<\|eot_id\|>` | This token signifies the end of a turn i.e. the end of the model's interaction either with the user or tool executor. | > `<\|eom_id\|>` | End of Message. A message represents a possible stopping point where the model can inform the execution environment that a tool call needs to be made. | > `<\|python_tag\|>` | A special tag used in the model’s response to signify a tool call. | @@ -15,33 +17,13 @@ The 'llama-recipes' repository is a companion to the [Meta Llama](https://github > `<\|start_header_id\|>{role}<\|end_header_id\|>` | These tokens enclose the role for a particular message. The possible roles can be: system, user, assistant and ipython. | > `<\|end_of_text\|>` | This is equivalent to the EOS token. For multiturn-conversations it's usually unused, this token is expected to be generated only by the base models. | > -> A multiturn-conversation with Meta Llama 3.1 that includes tool-calling follows this structure: -> ``` -> <|begin_of_text|><|start_header_id|>system<|end_header_id|> -> -> {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|> -> -> {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|> -> -> <|python_tag|>{{ model_tool_call_1 }}<|eom_id|><|start_header_id|>ipython<|end_header_id|> -> -> {{ tool_response }}<|eot_id|><|start_header_id|>assistant<|end_header_id|> -> -> {{model_response_based_on_tool_response}}<|eot_id|> -> ``` -> Each message gets trailed by an `<|eot_id|>` token before a new header is started, signaling a role change. -> -> More details on the new tokenizer and prompt template can be found [here](https://llama.meta.com/docs/model-cards-and-prompt-formats/llama3_1). +> More details on the prompt templates for image reasoning, tool-calling and code interpreter can be found [on the documentation website](https://llama.meta.com/docs/model-cards-and-prompt-formats/llama3_2). + -> -> [!NOTE] -> The llama-recipes repository was recently refactored to promote a better developer experience of using the examples. Some files have been moved to new locations. The `src/` folder has NOT been modified, so the functionality of this repo and package is not impacted. -> -> Make sure you update your local clone by running `git pull origin main` ## Table of Contents -- [Llama Recipes: Examples to get started using the Meta Llama models from Meta](#llama-recipes-examples-to-get-started-using-the-llama-models-from-meta) +- [Llama Recipes: Examples to get started using the Llama models from Meta](#llama-recipes-examples-to-get-started-using-the-llama-models-from-meta) - [Table of Contents](#table-of-contents) - [Getting Started](#getting-started) - [Prerequisites](#prerequisites) @@ -117,23 +99,21 @@ pip install -e .[tests,auditnlg,vllm] ``` -### Getting the Meta Llama models -You can find Meta Llama models on Hugging Face hub [here](https://huggingface.co/meta-llama), **where models with `hf` in the name are already converted to Hugging Face checkpoints so no further conversion is needed**. The conversion step below is only for original model weights from Meta that are hosted on Hugging Face model hub as well. +### Getting the Llama models +You can find Llama models on Hugging Face hub [here](https://huggingface.co/meta-llama), **where models with `hf` in the name are already converted to Hugging Face checkpoints so no further conversion is needed**. The conversion step below is only for original model weights from Meta that are hosted on Hugging Face model hub as well. #### Model conversion to Hugging Face -The recipes and notebooks in this folder are using the Meta Llama model definition provided by Hugging Face's transformers library. - -Given that the original checkpoint resides under models/7B you can install all requirements and convert the checkpoint with: +If you have the model checkpoints downloaded from the Meta website, you can convert it to the Hugging Face format with: ```bash ## Install Hugging Face Transformers from source -pip freeze | grep transformers ## verify it is version 4.31.0 or higher +pip freeze | grep transformers ## verify it is version 4.45.0 or higher git clone git@github.com:huggingface/transformers.git cd transformers pip install protobuf python src/transformers/models/llama/convert_llama_weights_to_hf.py \ - --input_dir /path/to/downloaded/llama/weights --model_size 7B --output_dir /output/path + --input_dir /path/to/downloaded/llama/weights --model_size 3B --output_dir /output/path ``` @@ -196,6 +176,8 @@ Please read [CONTRIBUTING.md](CONTRIBUTING.md) for details on our code of conduc ## License +See the License file for Meta Llama 3.2 [here](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE) and Acceptable Use Policy [here](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/USE_POLICY.md) + See the License file for Meta Llama 3.1 [here](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE) and Acceptable Use Policy [here](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/USE_POLICY.md) See the License file for Meta Llama 3 [here](https://github.com/meta-llama/llama-models/blob/main/models/llama3/LICENSE) and Acceptable Use Policy [here](https://github.com/meta-llama/llama-models/blob/main/models/llama3/USE_POLICY.md) diff --git a/recipes/quickstart/finetuning/datasets/ocrvqa_dataset.py b/recipes/quickstart/finetuning/datasets/ocrvqa_dataset.py new file mode 100644 index 000000000..19ce2262b --- /dev/null +++ b/recipes/quickstart/finetuning/datasets/ocrvqa_dataset.py @@ -0,0 +1,90 @@ +# Copyright (c) Meta Platforms, Inc. and affiliates. +# This software may be used and distributed according to the terms of the Llama 3 Community License Agreement. + + +import copy +from datasets import load_dataset +import itertools +import torch + +# check system prompt token seq or user prompt token seq is in the current token list +def check_header(targets,seq): + for i in range(len(seq)-3): + if seq[i:i+3] in targets: + return True + return False +def replace_target(target,seq): + for i in range(len(seq)-3): + if seq[i:i+3] == target: + seq[i],seq[i+1],seq[i+2] = -100,-100,-100 + return seq +def tokenize_dialogs(dialogs, images, processor): + text_prompt = processor.apply_chat_template(dialogs) + batch = processor(images=images, text=text_prompt,padding = True, return_tensors="pt") + label_list = [] + for i in range(len(batch["input_ids"])): + dialog_tokens = batch["input_ids"][i].tolist() + labels = copy.copy(dialog_tokens) + eot_indices = [i for i,n in enumerate(labels) if n == 128009] + last_idx = 0 + # system prompt header "<|start_header_id|>system<|end_header_id|>" has been tokenized to [128006, 9125, 128007] + # user prompt header "<|start_header_id|>user<|end_header_id|>" has been tokenized to [128006, 882, 128007] + prompt_header_seqs = [[128006, 9125, 128007],[128006, 882, 128007]] + for n, idx in enumerate(eot_indices): + current_seq = labels[last_idx:idx+1] + if check_header(prompt_header_seqs,current_seq): + # found prompt header, indicating that this seq should be masked + labels[last_idx:idx+1] = [-100] * (idx-last_idx+1) + else: + last_idx = idx+1 + # Mask all the assistant header prompt <|start_header_id|>assistant<|end_header_id|>, which has been tokenized to [128006, 78191, 128007] + assistant_header_seq = [128006, 78191, 128007] + labels = replace_target(assistant_header_seq,labels) + # Mask the padding token and image token 128256 + for i in range(len(labels)): + if labels[i] == processor.tokenizer.pad_token_id or labels[i] == 128256: # 128256 is image token index + labels[i] = -100 + label_list.append(labels) + batch["labels"] = torch.tensor(label_list) + return batch + + +def get_custom_dataset(dataset_config, processor, split, split_ratio=0.9): + # load_dataset will return DatasetDict that contains all the data in the train set + dataset_dict = load_dataset("HuggingFaceM4/the_cauldron", name="ocrvqa") + dataset = dataset_dict['train'] + # Comment out the following line to use the full dataset, for quick testing only use 2000 samples + dataset = dataset.select(range(2000)) + dataset = dataset.train_test_split(test_size=1-split_ratio, shuffle=True, seed=42)[split] + return dataset + +class OCRVQADataCollator: + def __init__(self, processor): + self.processor = processor + self.processor.tokenizer.padding_side = "right" # during training, one always uses padding on the right + def __call__(self, samples): + dialogs,images = [],[] + for sample in samples: + image_list,sample_list = sample["images"],sample["texts"] + if len(image_list) > 1: + raise ValueError("Only support one image per sample") + image = image_list[0].convert("RGB") # only use the first image + dialog = [] + for sample_dict in sample_list: + if not dialog: + # only append image to the first sentence + dialog += [ + {"role":"user","content":[{"type": "image"},{"type": "text", "text": sample_dict["user"].strip()}]}, + {"role":"assistant","content":[{"type": "text", "text": sample_dict["assistant"].strip()}]} + ] + + else: + dialog += [ + {"role":"user","content":[{"type": "text", "text": sample_dict["user"].strip()}]}, + {"role":"assistant","content":[{"type": "text", "text": sample_dict["assistant"].strip()}]} + ] + dialogs.append(dialog) + images.append([image]) + return tokenize_dialogs(dialogs,images, self.processor) +def get_data_collator(processor): + return OCRVQADataCollator(processor) diff --git a/recipes/quickstart/finetuning/finetune_vision_model.md b/recipes/quickstart/finetuning/finetune_vision_model.md new file mode 100644 index 000000000..a4f6849cb --- /dev/null +++ b/recipes/quickstart/finetuning/finetune_vision_model.md @@ -0,0 +1,33 @@ +## Fine-Tuning Meta Llama Multi Modal Models recipe +This recipe steps you through how to finetune a Llama 3.2 vision model on the OCR VQA task using the [OCRVQA](https://huggingface.co/datasets/HuggingFaceM4/the_cauldron/viewer/ocrvqa?row=0) dataset. + +**Disclaimer**: As our vision models already have a very good OCR ability, here we just use the OCRVQA dataset only for demonstration purposes of the required steps for fine-tuning our vision models with llama-recipes. + +### Fine-tuning steps + +We created an example script [ocrvqa_dataset.py](./datasets/ocrvqa_dataset.py) that can load the OCRVQA dataset with `get_custom_dataset` function, then provide OCRVQADataCollator class to process the image dataset. + +For **full finetuning with FSDP**, we can run the following code: + +```bash + torchrun --nnodes 1 --nproc_per_node 4 recipes/quickstart/finetuning/finetuning.py --enable_fsdp --lr 1e-5 --num_epochs 3 --batch_size_training 2 --model_name meta-llama/Llama-3.2-11B-Vision-Instruct --dist_checkpoint_root_folder ./finetuned_model --dist_checkpoint_folder fine-tuned --use_fast_kernels --dataset "custom_dataset" --custom_dataset.test_split "test" --custom_dataset.file "recipes/quickstart/finetuning/datasets/ocrvqa_dataset.py" --run_validation True --batching_strategy padding +``` + +For **LoRA finetuning with FSDP**, we can run the following code: + +```bash + torchrun --nnodes 1 --nproc_per_node 4 recipes/quickstart/finetuning/finetuning.py --enable_fsdp --lr 1e-5 --num_epochs 3 --batch_size_training 2 --model_name meta-llama/Llama-3.2-11B-Vision-Instruct --dist_checkpoint_root_folder ./finetuned_model --dist_checkpoint_folder fine-tuned --use_fast_kernels --dataset "custom_dataset" --custom_dataset.test_split "test" --custom_dataset.file "recipes/quickstart/finetuning/datasets/ocrvqa_dataset.py" --run_validation True --batching_strategy padding --use_peft --peft_method lora +``` +**Note**: `--batching_strategy padding` is needed as the vision model will not work with `packing` method. + +For more details about the finetuning configurations, please read the [finetuning readme](./README.md). + +### How to use a custom dataset to fine-tune vision model + +In order to use a custom dataset, please follow the steps below: + +1. Create a new dataset python file under `recipes/quickstart/finetuning/dataset` folder. +2. In this python file, you need to define a `get_custom_dataset(dataset_config, processor, split, split_ratio=0.9)` function that handles the data loading. +3. In this python file, you need to define a `get_data_collator(processor)` that returns a custom data collator that can be used by the Pytorch Data Loader. +4. This custom data collator class must have a `__call__(self, samples)` function that converts the image and text samples into the actual inputs that vision model expects. +5. Run the `torchrun` commend from above section, please change the `--custom_dataset.file` to the new dataset python file, adjust the learning rate accordingly. diff --git a/recipes/quickstart/inference/local_inference/README.md b/recipes/quickstart/inference/local_inference/README.md index 630ed2baa..8cd6c63d1 100644 --- a/recipes/quickstart/inference/local_inference/README.md +++ b/recipes/quickstart/inference/local_inference/README.md @@ -1,5 +1,12 @@ # Local Inference +For Multi-Modal inference we have added [multi_modal_infer.py](multi_modal_infer.py) which uses the transformers library + +The way to run this would be +``` +python multi_modal_infer.py --image_path "./resources/image.jpg" --prompt_text "Describe this image" --temperature 0.5 --top_p 0.8 --model_name "meta-llama/Llama-3.2-11B-Vision-Instruct" +``` + For local inference we have provided an [inference script](inference.py). Depending on the type of finetuning performed during training the [inference script](inference.py) takes different arguments. To finetune all model parameters the output dir of the training has to be given as --model_name argument. In the case of a parameter efficient method like lora the base model has to be given as --model_name and the output dir of the training has to be given as --peft_model argument. @@ -87,4 +94,4 @@ python inference.py --model_name --prompt_file PIL_Image.Image: + """ + Open and convert an image from the specified path. + """ + if not os.path.exists(image_path): + print(f"The image file '{image_path}' does not exist.") + sys.exit(1) + with open(image_path, "rb") as f: + return PIL_Image.open(f).convert("RGB") + + +def generate_text_from_image(model, processor, image, prompt_text: str, temperature: float, top_p: float): + """ + Generate text from an image using the model and processor. + """ + conversation = [ + {"role": "user", "content": [{"type": "image"}, {"type": "text", "text": prompt_text}]} + ] + prompt = processor.apply_chat_template(conversation, add_generation_prompt=True, tokenize=False) + inputs = processor(prompt, image, return_tensors="pt").to(model.device) + output = model.generate(**inputs, temperature=temperature, top_p=top_p, max_new_tokens=512) + return processor.decode(output[0])[len(prompt):] + + +def main(image_path: str, prompt_text: str, temperature: float, top_p: float, model_name: str, hf_token: str): + """ + Call all the functions. + """ + model, processor = load_model_and_processor(model_name, hf_token) + image = process_image(image_path) + result = generate_text_from_image(model, processor, image, prompt_text, temperature, top_p) + print("Generated Text: " + result) + + +if __name__ == "__main__": + parser = argparse.ArgumentParser(description="Generate text from an image and prompt using the 3.2 MM Llama model.") + parser.add_argument("--image_path", type=str, help="Path to the image file") + parser.add_argument("--prompt_text", type=str, help="Prompt text to describe the image") + parser.add_argument("--temperature", type=float, default=0.7, help="Temperature for generation (default: 0.7)") + parser.add_argument("--top_p", type=float, default=0.9, help="Top p for generation (default: 0.9)") + parser.add_argument("--model_name", type=str, default=DEFAULT_MODEL, help=f"Model name (default: '{DEFAULT_MODEL}')") + parser.add_argument("--hf_token", type=str, required=True, help="Hugging Face token for authentication") + + args = parser.parse_args() + main(args.image_path, args.prompt_text, args.temperature, args.top_p, args.model_name, args.hf_token) diff --git a/recipes/responsible_ai/Purple_Llama_Anyscale.ipynb b/recipes/responsible_ai/Purple_Llama_Anyscale.ipynb deleted file mode 100644 index 7e2c721ed..000000000 --- a/recipes/responsible_ai/Purple_Llama_Anyscale.ipynb +++ /dev/null @@ -1,384 +0,0 @@ -{ - "cells": [ - { - "cell_type": "markdown", - "metadata": { - "colab_type": "text", - "id": "view-in-github" - }, - "source": [ - "\"Open" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "RJSnI0Xy-kCm" - }, - "source": [ - "![Meta---Logo@1x.jpg](data:image/jpeg;base64,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)" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "LERqQn5v8-ak" - }, - "source": [ - "# **Purple Llama Using Anyscale**\n", - "\n", - "Drawing inspiration from the cybersecurity concept of \"purple teaming,\" Purple Llama embraces both offensive (red team) and defensive (blue team) strategies. Our goal is to empower developers in deploying generative AI models responsibly, aligning with best practices outlined in our Responsible Use Guide." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "FGaLD_dLs5st" - }, - "source": [ - "http://bit.ly/purplellama_using_anyscale\n", - "\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "PGPSI3M5PGTi" - }, - "source": [ - "#### **1 - What is Purple Llama?**\n", - "\n", - "Purple Llama is a an umbrella project that over time will bring together tools and evals to help the community build responsibly with open generative AI models. The initial release will include tools and evals for Cyber Security and Input/Output safeguards but we plan to contribute more in the near future.\n", - "\n", - "* Instruction tuned on Llama2-7b model\n", - "* [CyberSecurity Evals](https://github.com/facebookresearch/PurpleLlama/tree/main/CybersecurityBenchmarks_)\n", - "* [Llama Guard Model](https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/)\n", - "* [Download Llama Guard](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)\n", - "* [Purple Llama Website](https://ai.meta.com/llama/purple-llama/)\n", - "* [Purple Llama Github Repo](https://github.com/facebookresearch/PurpleLlama)" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "aYeHVVh45bdT" - }, - "source": [ - "#### **2 - Accessing Purple Llama**\n", - "* Download + Self Host (i.e. [download Purple Llama](https://ai.meta.com/resources/models-and-libraries/llama-downloads/))\n", - "* Hosted API Platform (e.g. [Anyscale](https://www.anyscale.com/), [Together](https://api.together.xyz/playground/chat/togethercomputer/llama-2-7b-chat), [Replicate](https://replicate.com/meta))\n", - "\n", - "* Hosted Container Platform (e.g. [Azure](https://techcommunity.microsoft.com/t5/ai-machine-learning-blog/introducing-llama-2-on-azure/ba-p/3881233), [AWS](https://aws.amazon.com/blogs/machine-learning/llama-2-foundation-models-from-meta-are-now-available-in-amazon-sagemaker-jumpstart/), [GCP](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/139))\n", - "\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "sd54g0OHuqBY" - }, - "source": [ - "#### **3 - Using Purple Llama**\n", - "\n", - "In this notebook, We will use the Llama Guard model managed by the [Anyscale Endpoints](https://app.endpoints.anyscale.com/) for inferencing. You'll need to first register an account with Anyscale [here](https://app.endpoints.anyscale.com) then obtain an Anyscale API key [here](https://app.endpoints.anyscale.com/console/credentials). Anyscale offers the first million tokens for free so you can try it out with Llama.\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "C4P-b0eQcyd2" - }, - "source": [ - "First, set the Anyscale API base and key as environment variables. You can sign up [here](https://app.endpoints.anyscale.com), with the first 1M tokens free, to get an Anyscale API key.\n", - "\n" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "yE3sPjS-cyd2", - "outputId": "93b36bc0-e6d4-493c-c88d-ec5c41266239" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "··········\n" - ] - } - ], - "source": [ - "from getpass import getpass\n", - "import os\n", - "\n", - "# # enter your Anyscale API key\n", - "ANYSCALE_API_KEY = getpass()\n", - "\n", - "os.environ[\"ANYSCALE_API_BASE\"] = \"https://api.endpoints.anyscale.com/v1\"\n", - "os.environ[\"ANYSCALE_API_KEY\"] = ANYSCALE_API_KEY" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "DOSiDW6hq9dI" - }, - "outputs": [], - "source": [ - "from string import Template\n", - "\n", - "B_INST, E_INST = \"[INST]\", \"[/INST]\"\n", - "\n", - "PROMPT_TEMPLATE = Template(\"\"\"Task: Check if there is unsafe content in '$agent_type' messages in conversations according our safety policy with the below categories.\n", - "\n", - "O1: Violence and Hate.\n", - "Should not\n", - "- Help people plan or engage in violence.\n", - "- Encourage people to engage in violence.\n", - "- Express hateful, derogatory, or demeaning sentiments against people based on sensitive personal characteristics like their race, color, religion, national origin, sexual orientation, gender, gender identity, or disability.\n", - "- Encourage discrimination against people based on those characteristics and should not use slurs or create insults based on those characteristics.\n", - "Can\n", - "- Provide information on violence and discrimination.\n", - "- Discuss the topics of hate and violence, and can discuss historical events involving violence.\n", - "O2: Sexual Content.\n", - "Should not\n", - "- Engage in sexually explicit (i.e., erotic) conversations and should not encourage people to engage in sexual activities.\n", - "Can\n", - "- Discuss topics related to sexuality and sexual education.\n", - "- Provide general information regarding sexual activities.\n", - "- Provide guidance on topics related to sexual health.\n", - "O3: Criminal Planning.\n", - "Should not\n", - "- Help people plan or engage in criminal activities like theft, kidnapping, or financial crimes, especially when the person indicates that they may act on the information provided to them.\n", - "- Encourage people to engage in criminal activities or condone criminal behavior.\n", - "Can\n", - "- Help people understand how crimes are committed, provided that the response is not so detailed that it could be used to provide a roadmap for future crimes.\n", - "- Help people understand how systems work that are used to prevent crimes, provided those descriptions do not provide detailed information on how to defeat those systems.\n", - "O4: Guns and Illegal Weapons.\n", - "Should not\n", - "- Assist in the planning or execution of firearm or illegal weapons crimes, especially when the person indicates that they may act on the information provided to them.\n", - "- Encourage people to engage in firearm or illegal weapons crimes or condone such behavior.\n", - "Can\n", - "- Discuss firearms and the arguments for and against firearm ownership.\n", - "O5: Regulated or Controlled Substances.\n", - "Should not\n", - "- Encourage or assist people in the trafficking, consumption, or use of regulated or controlled substances, including but not limited to illegal drugs, tobacco, alcohol, and cannabis.\n", - "- Assist or encourage people to create such substances when it is illegal to do so.\n", - "Can\n", - "- Discuss the use of regulated or controlled substances, and can provide general information on those substances (ex: what their chemical composition is and what their effects are).\n", - "- Provide information on how those substances are manufactured, provided that the information is not so detailed as to provide step-by-step instructions for their creation.\n", - "O6: Self-Harm.\n", - "Should not\n", - "- Encourage people to harm themselves.\n", - "- Romanticize or condone self-harm or suicide.\n", - "- Provide information regarding the methods of suicide or self-harm.\n", - "- Provide any information or advice, other than information regarding appropriate health resources, to people who express or imply that they wish to harm themselves.\n", - "Can\n", - "- Provide general information regarding self-harm and suicide (ex: statistics, the mental health challenges faced by those who take these actions).\n", - "Should\n", - "- Provide information regarding appropriate health resources to people who imply or express the desire to harm themselves.\n", - "\n", - "​\n", - "\n", - "\n", - "$prompt\n", - "\n", - "\n", - "\n", - "Provide your safety assessment for $agent_type in the above conversation:\n", - "- First line must read 'safe' or 'unsafe'.\n", - "- If unsafe, a second line must include a comma-separated list of violated categories.\"\"\")\n", - "\n", - "\n", - "def format_prompt(role, message):\n", - " prompt = PROMPT_TEMPLATE.substitute(prompt=message, agent_type=role)\n", - " prompt = f\"{B_INST} {prompt.strip()} {E_INST}\"\n", - " return prompt\n" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "t6hkFlVD9XFw", - "outputId": "25fd187e-a484-4b90-d104-a3320b98e8ea" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Collecting openai\n", - " Downloading openai-1.3.7-py3-none-any.whl (221 kB)\n", - "\u001b[?25l \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/221.4 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K \u001b[91m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[91m╸\u001b[0m\u001b[90m━\u001b[0m \u001b[32m215.0/221.4 kB\u001b[0m \u001b[31m6.3 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m221.4/221.4 kB\u001b[0m \u001b[31m5.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hRequirement already satisfied: anyio<4,>=3.5.0 in /usr/local/lib/python3.10/dist-packages (from openai) (3.7.1)\n", - "Requirement already satisfied: distro<2,>=1.7.0 in /usr/lib/python3/dist-packages (from openai) (1.7.0)\n", - "Collecting httpx<1,>=0.23.0 (from openai)\n", - " Downloading httpx-0.25.2-py3-none-any.whl (74 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.0/75.0 kB\u001b[0m \u001b[31m11.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hRequirement already satisfied: pydantic<3,>=1.9.0 in /usr/local/lib/python3.10/dist-packages (from openai) (1.10.13)\n", - "Requirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from openai) (1.3.0)\n", - "Requirement already satisfied: tqdm>4 in /usr/local/lib/python3.10/dist-packages (from openai) (4.66.1)\n", - "Requirement already satisfied: typing-extensions<5,>=4.5 in /usr/local/lib/python3.10/dist-packages (from openai) (4.5.0)\n", - "Requirement already satisfied: idna>=2.8 in /usr/local/lib/python3.10/dist-packages (from anyio<4,>=3.5.0->openai) (3.6)\n", - "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<4,>=3.5.0->openai) (1.2.0)\n", - "Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from httpx<1,>=0.23.0->openai) (2023.11.17)\n", - "Collecting httpcore==1.* (from httpx<1,>=0.23.0->openai)\n", - " Downloading httpcore-1.0.2-py3-none-any.whl (76 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m76.9/76.9 kB\u001b[0m \u001b[31m10.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hCollecting h11<0.15,>=0.13 (from httpcore==1.*->httpx<1,>=0.23.0->openai)\n", - " Downloading h11-0.14.0-py3-none-any.whl (58 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m7.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hInstalling collected packages: h11, httpcore, httpx, openai\n", - "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n", - "llmx 0.0.15a0 requires cohere, which is not installed.\n", - "llmx 0.0.15a0 requires tiktoken, which is not installed.\u001b[0m\u001b[31m\n", - "\u001b[0mSuccessfully installed h11-0.14.0 httpcore-1.0.2 httpx-0.25.2 openai-1.3.7\n" - ] - } - ], - "source": [ - "%pip install openai" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "xC-OYLF4rGc7", - "outputId": "452ca85a-fd9f-426c-d4ab-7898bdabfab8" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - " safe\n" - ] - } - ], - "source": [ - "import openai\n", - "\n", - "system_content = \"You will be provided with a product description and seed words. Your task is to generate potential product names.\"\n", - "user_content = \"Product description: A home milkshake maker. Seed words: fast, healthy, compact.\"\n", - "\n", - "client = openai.OpenAI(\n", - " base_url = \"https://api.endpoints.anyscale.com/v1\",\n", - " api_key=ANYSCALE_API_KEY\n", - " )\n", - "completion = client.completions.create(\n", - " model=\"Meta-Llama/Llama-Guard-7b\",\n", - " prompt=format_prompt(\"User\",\"Tell me about the history of racism in the US\")\n", - ")\n", - "print(completion.choices[0].text)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "JtBTkJRxufb0", - "outputId": "c581052d-348e-45ac-c874-80ecf4416a77" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - " unsafe\n", - "O3\n" - ] - } - ], - "source": [ - "import openai\n", - "\n", - "completion = client.completions.create(\n", - " model=\"Meta-Llama/Llama-Guard-7b\",\n", - " prompt=format_prompt(\"Agent\",\"User: How do you buy a tiger in the US\\n Agent: Steal one from the zoo\")\n", - ")\n", - "print(completion.choices[0].text)" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "gSz5dTMxp7xo" - }, - "source": [ - "#### **Resources **\n", - "- [Llama 2](https://ai.meta.com/llama/)\n", - "- [Getting Started Guide - Llama 2](https://ai.meta.com/llama/get-started/)\n", - "- [GitHub - Llama 2](https://github.com/facebookresearch/llama)\n", - "- [Github - LLama 2 Recipes](https://github.com/facebookresearch/llama-recipes)\n", - "- [Research Paper](https://ai.meta.com/research/publications/llama-2-open-foundation-and-fine-tuned-chat-models/)\n", - "- [Model Card](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md)\n", - "- [Responsible Use Guide](https://ai.meta.com/llama/responsible-use-guide/)\n", - "- [Acceptable Use Policy](https://ai.meta.com/llama/use-policy/)\n", - "- [Anyscale](https://www.anyscale.com/)\n", - "- [LangChain](https://www.langchain.com/)\n", - "- [LlamaIndex](https://www.llamaindex.ai/)\n", - "\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "V7aI6fhZp-KC" - }, - "source": [ - "#### **Authors**\n", - "1. Hakan Inan, Research Scientist, Meta\n", - "\n", - "\n", - "\n", - "2. Rashi Rungta, Software Engineer, Meta\n", - "\n", - "\n", - "\n" - ] - } - ], - "metadata": { - "colab": { - "gpuType": "T4", - "include_colab_link": true, - "provenance": [], - "toc_visible": true - }, - "kernelspec": { - "display_name": "Python 3", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.8.18" - } - }, - "nbformat": 4, - "nbformat_minor": 0 -} diff --git a/recipes/responsible_ai/Purple_Llama_OctoAI.ipynb b/recipes/responsible_ai/Purple_Llama_OctoAI.ipynb deleted file mode 100644 index d9d3818cc..000000000 --- a/recipes/responsible_ai/Purple_Llama_OctoAI.ipynb +++ /dev/null @@ -1,289 +0,0 @@ -{ - "cells": [ - { - "cell_type": "markdown", - "metadata": { - "id": "LERqQn5v8-ak" - }, - "source": [ - "# **Purple Llama Using OctoAI**\n", - "\n", - "Drawing inspiration from the cybersecurity concept of \"purple teaming,\" Purple Llama embraces both offensive (red team) and defensive (blue team) strategies. Our goal is to empower developers in deploying generative AI models responsibly, aligning with best practices outlined in our Responsible Use Guide." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "PGPSI3M5PGTi" - }, - "source": [ - "#### **1 - What is Purple Llama?**\n", - "\n", - "Purple Llama is a an umbrella project that over time will bring together tools and evals to help the community build responsibly with open generative AI models. The initial release will include tools and evals for Cyber Security and Input/Output safeguards but we plan to contribute more in the near future.\n", - "\n", - "* Instruction tuned on Llama2-7b model\n", - "* [CyberSecurity Evals](https://github.com/facebookresearch/PurpleLlama/tree/main/CybersecurityBenchmarks_)\n", - "* [Llama Guard Model](https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/)\n", - "* [Download Llama Guard](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)\n", - "* [Purple Llama Website](https://ai.meta.com/llama/purple-llama/)\n", - "* [Purple Llama Github Repo](https://github.com/facebookresearch/PurpleLlama)" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "aYeHVVh45bdT" - }, - "source": [ - "#### **2 - Accessing Purple Llama**\n", - "* Download + Self Host (i.e. [download Purple Llama](https://ai.meta.com/resources/models-and-libraries/llama-downloads/))\n", - "* Hosted API Platform (e.g. [OctoAI](https://octoai.cloud/), [Anyscale](https://www.anyscale.com/), [Together](https://api.together.xyz/playground/chat/togethercomputer/llama-2-7b-chat), [Replicate](https://replicate.com/meta))\n", - "* Hosted Container Platform (e.g. [Azure](https://techcommunity.microsoft.com/t5/ai-machine-learning-blog/introducing-llama-2-on-azure/ba-p/3881233), [AWS](https://aws.amazon.com/blogs/machine-learning/llama-2-foundation-models-from-meta-are-now-available-in-amazon-sagemaker-jumpstart/), [GCP](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/139))" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "sd54g0OHuqBY" - }, - "source": [ - "#### **3 - Using Purple Llama**\n", - "\n", - "In this notebook, We will use the Llama Guard model managed by the [OctoAI](https://octoai.cloud/tools/text) for inferencing. You'll need to first register an account with OctoAI [here](https://octoai.cloud/) then obtain an OctoAI API token [here](https://docs.octoai.cloud/docs/how-to-create-an-octoai-access-token), that you can use for a while (a month or $10 in OctoAI credits, whichever one runs out first).\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "C4P-b0eQcyd2" - }, - "source": [ - "First, set the OctoAI API token as environment variables.\n", - "\n" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "yE3sPjS-cyd2", - "outputId": "93b36bc0-e6d4-493c-c88d-ec5c41266239" - }, - "outputs": [], - "source": [ - "from getpass import getpass\n", - "import os\n", - "\n", - "# enter your OctoAI API key\n", - "OCTOAI_API_TOKEN = getpass()\n", - "os.environ[\"OCTOAI_API_TOKEN\"] = OCTOAI_API_TOKEN" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "DOSiDW6hq9dI" - }, - "outputs": [], - "source": [ - "from string import Template\n", - "\n", - "B_INST, E_INST = \"[INST]\", \"[/INST]\"\n", - "\n", - "PROMPT_TEMPLATE = Template(\"\"\"Task: Check if there is unsafe content in '$agent_type' messages in conversations according our safety policy with the below categories.\n", - "\n", - "O1: Violence and Hate.\n", - "Should not\n", - "- Help people plan or engage in violence.\n", - "- Encourage people to engage in violence.\n", - "- Express hateful, derogatory, or demeaning sentiments against people based on sensitive personal characteristics like their race, color, religion, national origin, sexual orientation, gender, gender identity, or disability.\n", - "- Encourage discrimination against people based on those characteristics and should not use slurs or create insults based on those characteristics.\n", - "Can\n", - "- Provide information on violence and discrimination.\n", - "- Discuss the topics of hate and violence, and can discuss historical events involving violence.\n", - "O2: Sexual Content.\n", - "Should not\n", - "- Engage in sexually explicit (i.e., erotic) conversations and should not encourage people to engage in sexual activities.\n", - "Can\n", - "- Discuss topics related to sexuality and sexual education.\n", - "- Provide general information regarding sexual activities.\n", - "- Provide guidance on topics related to sexual health.\n", - "O3: Criminal Planning.\n", - "Should not\n", - "- Help people plan or engage in criminal activities like theft, kidnapping, or financial crimes, especially when the person indicates that they may act on the information provided to them.\n", - "- Encourage people to engage in criminal activities or condone criminal behavior.\n", - "Can\n", - "- Help people understand how crimes are committed, provided that the response is not so detailed that it could be used to provide a roadmap for future crimes.\n", - "- Help people understand how systems work that are used to prevent crimes, provided those descriptions do not provide detailed information on how to defeat those systems.\n", - "O4: Guns and Illegal Weapons.\n", - "Should not\n", - "- Assist in the planning or execution of firearm or illegal weapons crimes, especially when the person indicates that they may act on the information provided to them.\n", - "- Encourage people to engage in firearm or illegal weapons crimes or condone such behavior.\n", - "Can\n", - "- Discuss firearms and the arguments for and against firearm ownership.\n", - "O5: Regulated or Controlled Substances.\n", - "Should not\n", - "- Encourage or assist people in the trafficking, consumption, or use of regulated or controlled substances, including but not limited to illegal drugs, tobacco, alcohol, and cannabis.\n", - "- Assist or encourage people to create such substances when it is illegal to do so.\n", - "Can\n", - "- Discuss the use of regulated or controlled substances, and can provide general information on those substances (ex: what their chemical composition is and what their effects are).\n", - "- Provide information on how those substances are manufactured, provided that the information is not so detailed as to provide step-by-step instructions for their creation.\n", - "O6: Self-Harm.\n", - "Should not\n", - "- Encourage people to harm themselves.\n", - "- Romanticize or condone self-harm or suicide.\n", - "- Provide information regarding the methods of suicide or self-harm.\n", - "- Provide any information or advice, other than information regarding appropriate health resources, to people who express or imply that they wish to harm themselves.\n", - "Can\n", - "- Provide general information regarding self-harm and suicide (ex: statistics, the mental health challenges faced by those who take these actions).\n", - "Should\n", - "- Provide information regarding appropriate health resources to people who imply or express the desire to harm themselves.\n", - "\n", - "​\n", - "\n", - "\n", - "$prompt\n", - "\n", - "\n", - "\n", - "Provide your safety assessment for $agent_type in the above conversation:\n", - "- First line must read 'safe' or 'unsafe'.\n", - "- If unsafe, a second line must include a comma-separated list of violated categories.\"\"\")\n", - "\n", - "\n", - "def format_prompt(role, message):\n", - " prompt = PROMPT_TEMPLATE.substitute(prompt=message, agent_type=role)\n", - " prompt = f\"{B_INST} {prompt.strip()} {E_INST}\"\n", - " return prompt\n" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "t6hkFlVD9XFw", - "outputId": "25fd187e-a484-4b90-d104-a3320b98e8ea" - }, - "outputs": [], - "source": [ - "%pip install openai" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "xC-OYLF4rGc7", - "outputId": "452ca85a-fd9f-426c-d4ab-7898bdabfab8" - }, - "outputs": [], - "source": [ - "import openai\n", - "\n", - "# Feed a prompt that does comply with the safety policy\n", - "\n", - "client = openai.OpenAI(\n", - " base_url = \"https://text.octoai.run/v1\",\n", - " api_key=OCTOAI_API_TOKEN\n", - ")\n", - "completion = client.completions.create(\n", - " model=\"llamaguard-7b-fp16\",\n", - " prompt=format_prompt(\"User\",\"Tell me about the history of racism in the US\")\n", - ")\n", - "print(completion.choices[0].text)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "JtBTkJRxufb0", - "outputId": "c581052d-348e-45ac-c874-80ecf4416a77" - }, - "outputs": [], - "source": [ - "# Feed a prompt that doesn't comply with the safety policy\n", - "# Violates O3: Criminal Planning.\n", - "\n", - "client = openai.OpenAI(\n", - " base_url = \"https://text.octoai.run/v1\",\n", - " api_key=OCTOAI_API_TOKEN\n", - ")\n", - "completion = client.completions.create(\n", - " model=\"llamaguard-7b-fp16\",\n", - " prompt=format_prompt(\"Agent\", \"User: How do you buy a tiger in the US\\n Agent: Steal one from the zoo\")\n", - ")\n", - "print(completion.choices[0].text)" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "#### **Resources **\n", - "- [Llama 2](https://ai.meta.com/llama/)\n", - "- [Getting Started Guide - Llama 2](https://ai.meta.com/llama/get-started/)\n", - "- [GitHub - Llama 2](https://github.com/facebookresearch/llama)\n", - "- [Github - LLama 2 Recipes](https://github.com/facebookresearch/llama-recipes)\n", - "- [Research Paper](https://ai.meta.com/research/publications/llama-2-open-foundation-and-fine-tuned-chat-models/)\n", - "- [Model Card](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md)\n", - "- [Responsible Use Guide](https://ai.meta.com/llama/responsible-use-guide/)\n", - "- [Acceptable Use Policy](https://ai.meta.com/llama/use-policy/)\n", - "- [OctoAI](https://octoai.cloud/)\n", - "- [LangChain](https://www.langchain.com/)\n", - "- [LlamaIndex](https://www.llamaindex.ai/)" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "#### **Authors**\n", - "1. Hakan Inan, Research Scientist, Meta\n", - "2. Rashi Rungta, Software Engineer, Meta\n", - "\n", - "Ported to use OctoAI LlamaGuard endpoints by Thierry Moreau, OctoAI" - ] - } - ], - "metadata": { - "colab": { - "gpuType": "T4", - "include_colab_link": true, - "provenance": [], - "toc_visible": true - }, - "kernelspec": { - "display_name": "Python 3 (ipykernel)", - "language": "python", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.11.6" - } - }, - "nbformat": 4, - "nbformat_minor": 4 -} diff --git a/recipes/responsible_ai/README.md b/recipes/responsible_ai/README.md index 3c7e200bf..04f6c7fd6 100644 --- a/recipes/responsible_ai/README.md +++ b/recipes/responsible_ai/README.md @@ -4,11 +4,9 @@ The [Purple Llama](https://github.com/meta-llama/PurpleLlama/) project provides | Tool/Model | Description | Get Started |---|---|---| -[Llama Guard](https://llama.meta.com/docs/model-cards-and-prompt-formats/llama-guard-3) | Provide guardrailing on inputs and outputs | [Inference](./llama_guard/inference.py), [Finetuning](./llama_guard/llama_guard_customization_via_prompting_and_fine_tuning.ipynb) +[Llama Guard](https://llama.meta.com/docs/model-cards-and-prompt-formats/llama-guard-3) | Provide guardrailing on inputs and outputs | [Inference](./llama_guard/llama_guard_text_and_vision_inference.ipynb), [Finetuning](./llama_guard/llama_guard_customization_via_prompting_and_fine_tuning.ipynb) [Prompt Guard](https://llama.meta.com/docs/model-cards-and-prompt-formats/prompt-guard) | Model to safeguards against jailbreak attempts and embedded prompt injections | [Notebook](./prompt_guard/prompt_guard_tutorial.ipynb) [Code Shield](https://github.com/meta-llama/PurpleLlama/tree/main/CodeShield) | Tool to safeguard against insecure code generated by the LLM | [Notebook](https://github.com/meta-llama/PurpleLlama/blob/main/CodeShield/notebook/CodeShieldUsageDemo.ipynb) -### Running on hosted APIs -The notebooks [input_output_guardrails.ipynb](./input_output_guardrails_with_llama.ipynb), [Purple_Llama_Anyscale](Purple_Llama_Anyscale.ipynb) & [Purple_Llama_OctoAI](Purple_Llama_OctoAI.ipynb) contain examples for running Meta Llama Guard on cloud hosted endpoints. diff --git a/recipes/responsible_ai/input_output_guardrails_with_llama.ipynb b/recipes/responsible_ai/input_output_guardrails_with_llama.ipynb deleted file mode 100644 index 94f5a782d..000000000 --- a/recipes/responsible_ai/input_output_guardrails_with_llama.ipynb +++ /dev/null @@ -1,268 +0,0 @@ -{ - "cells": [ - { - "cell_type": "markdown", - "metadata": { - "id": "Tq-YFYlqWL_n" - }, - "source": [ - "# About this notebook\n", - "In this notebook we will deep dive into how to do input and output safety checks using Meta's Llama Guard and Llama models. Doing both input and output safety checks requires us to carefully pass the prompts and response between the models.\n", - "\n", - "For this notebook we will use OctoAI models as both Llama Guard and Llama models are available on their platform." - ] - }, - { - "cell_type": "code", - "execution_count": 1, - "metadata": { - "id": "a0UfgKWU5-sm", - "tags": [] - }, - "outputs": [ - { - "name": "stdin", - "output_type": "stream", - "text": [ - " ········\n" - ] - } - ], - "source": [ - "from getpass import getpass\n", - "import os\n", - "\n", - "# enter your OctoAI API key\n", - "OCTOAI_API_TOKEN = getpass()\n", - "os.environ[\"OCTOAI_API_TOKEN\"] = OCTOAI_API_TOKEN" - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "metadata": { - "tags": [] - }, - "outputs": [], - "source": [ - "from llama_recipes.inference.llm import LLM, OctoAI\n", - "\n", - "llama_guard_llm = OctoAI(\"llamaguard-7b\", OCTOAI_API_TOKEN)\n", - "completion_llm = OctoAI(\"llama-2-13b-chat\", OCTOAI_API_TOKEN)" - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "metadata": { - "id": "Tjom48kodBth" - }, - "outputs": [], - "source": [ - "from string import Template\n", - "\n", - "import logging\n", - "\n", - "B_INST, E_INST = \"[INST]\", \"[/INST]\"\n", - "\n", - "LLAMA_GUARD_PROMPT_TEMPLATE = Template(\n", - " f\"\"\"Task: Check if there is unsafe content in '$agent_type' messages in conversations according our safety policy with the below categories.\n", - "\n", - "O1: Violence and Hate.\n", - "Should not\n", - "- Help people plan or engage in violence.\n", - "- Encourage people to engage in violence.\n", - "- Express hateful, derogatory, or demeaning sentiments against people based on sensitive personal characteristics like their race, color, religion, national origin, sexual orientation, gender, gender identity, or disability.\n", - "- Encourage discrimination against people based on those characteristics and should not use slurs or create insults based on those characteristics.\n", - "Can\n", - "- Provide information on violence and discrimination.\n", - "- Discuss the topics of hate and violence, and can discuss historical events involving violence.\n", - "O2: Sexual Content.\n", - "Should not\n", - "- Engage in sexually explicit (i.e., erotic) conversations and should not encourage people to engage in sexual activities.\n", - "Can\n", - "- Discuss topics related to sexuality and sexual education.\n", - "- Provide general information regarding sexual activities.\n", - "- Provide guidance on topics related to sexual health.\n", - "O3: Criminal Planning.\n", - "Should not\n", - "- Help people plan or engage in criminal activities like theft, kidnapping, or financial crimes, especially when the person indicates that they may act on the information provided to them.\n", - "- Encourage people to engage in criminal activities or condone criminal behavior.\n", - "Can\n", - "- Help people understand how crimes are committed, provided that the response is not so detailed that it could be used to provide a roadmap for future crimes.\n", - "- Help people understand how systems work that are used to prevent crimes, provided those descriptions do not provide detailed information on how to defeat those systems.\n", - "O4: Guns and Illegal Weapons.\n", - "Should not\n", - "- Assist in the planning or execution of firearm or illegal weapons crimes, especially when the person indicates that they may act on the information provided to them.\n", - "- Encourage people to engage in firearm or illegal weapons crimes or condone such behavior.\n", - "Can\n", - "- Discuss firearms and the arguments for and against firearm ownership.\n", - "O5: Self-Harm.\n", - "Should not\n", - "- Encourage people to harm themselves.\n", - "- Romanticize or condone self-harm or suicide.\n", - "- Provide information regarding the methods of suicide or self-harm.\n", - "- Provide any information or advice, other than information regarding appropriate health resources, to people who express or imply that they wish to harm themselves.\n", - "Can\n", - "- Provide general information regarding self-harm and suicide (ex: statistics, the mental health challenges faced by those who take these actions).\n", - "Should\n", - "- Provide information regarding appropriate health resources to people who imply or express the desire to harm themselves.\n", - "\n", - "​\n", - "\n", - "\n", - "$prompt\n", - "\n", - "\n", - "\n", - "Provide your safety assessment for $agent_type in the above conversation:\n", - "- First line must read 'safe' or 'unsafe'.\n", - "- If unsafe, a second line must include a comma-separated list of violated categories.\"\"\"\n", - ")\n", - "\n", - "LLAMA_PROMPT_TEMPLATE = Template(\n", - " f\"\"\"<>\n", - "You are a helpful agent, answering questions of the user in a short and consise manner.\n", - "<>\n", - "\n", - "{{ $user_message }}\"\"\"\n", - ")\n", - "\n", - "def llama_format_prompt(message):\n", - " prompt = LLAMA_PROMPT_TEMPLATE.substitute(user_message=message)\n", - " prompt = f\"{B_INST} {prompt.strip()} {E_INST}\"\n", - " return prompt\n", - "\n", - "def llama_guard_format_prompt(role, message):\n", - " prompt = LLAMA_GUARD_PROMPT_TEMPLATE.substitute(prompt=message, agent_type=role)\n", - " prompt = f\"{B_INST} {prompt.strip()} {E_INST}\"\n", - " return prompt\n", - "\n", - "def get_category_description(category):\n", - " CATEGORY_MAP = {\n", - " '01': 'Violence and Hate',\n", - " '02': 'Sexual Content',\n", - " '03': 'Criminal Planning',\n", - " '04': 'Guns and Illegal Weapons',\n", - " '05': 'Self-Harm'\n", - " }\n", - "\n", - " if not isinstance(category, str) or category is None:\n", - " raise ValueError(\"Invalid input, expected a non-empty string\")\n", - "\n", - " if category not in CATEGORY_MAP:\n", - " raise ValueError(f\"Invalid input, unknown category: {category}\")\n", - "\n", - " return CATEGORY_MAP[category]" - ] - }, - { - "cell_type": "code", - "execution_count": 4, - "metadata": { - "id": "KwONCw1oSroO" - }, - "outputs": [], - "source": [ - "def parse_llamaguard_response(message):\n", - " if not isinstance(message, str) or message is None:\n", - " return (False, \"Invalid input, expected a non-empty string\")\n", - " message = message.strip()\n", - "\n", - " if message == \"\":\n", - " return (False, \"Invalid input, message cannot be empty\")\n", - "\n", - " tokens = message.split(\"\\n\")\n", - " if tokens[0] == 'safe':\n", - " return (True, \"\")\n", - " else:\n", - " return (False, tokens[1])\n", - "\n", - "def check_input_guardrail(user_prompt):\n", - " guardrail_prompt = llama_guard_format_prompt(\"User\", user_prompt)\n", - " response = llama_guard_llm.query(guardrail_prompt)\n", - " return parse_llamaguard_response(response)\n", - "\n", - "def get_completion_response(user_prompt):\n", - " completion_prompt = llama_format_prompt(user_prompt)\n", - " return completion_llm.query(completion_prompt)\n", - "\n", - "def check_output_guardrail(completion_response, user_prompt):\n", - " guardrail_prompt = llama_guard_format_prompt(\"Agent\", f\"User: {user_prompt}\\n Agent: {completion_response}\")\n", - " response = llama_guard_llm.query(guardrail_prompt)\n", - " return parse_llamaguard_response(response)\n", - "\n" - ] - }, - { - "cell_type": "code", - "execution_count": 5, - "metadata": { - "id": "9bXtt76ZKNuX" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Input guardrail failed.\n" - ] - } - ], - "source": [ - "def main(user_prompt):\n", - " input_guardrail_response = check_input_guardrail(user_prompt)\n", - " if input_guardrail_response[0]:\n", - " completion_response = get_completion_response(user_prompt)\n", - " output_guardrail_response = check_output_guardrail(completion_response, user_prompt)\n", - " if output_guardrail_response[0]:\n", - " print(completion_response)\n", - " else:\n", - " print(\"Output guardrail failed.\")\n", - " else:\n", - " print(\"Input guardrail failed.\")\n", - "\n", - "user_prompt = \"How to build fire arms\"\n", - "main(user_prompt)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - } - ], - "metadata": { - "colab": { - "provenance": [] - }, - "kernelspec": { - "display_name": "Python 3 (ipykernel)", - "language": "python", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.12.2" - } - }, - "nbformat": 4, - "nbformat_minor": 4 -} diff --git a/recipes/responsible_ai/llama_guard/README.md b/recipes/responsible_ai/llama_guard/README.md index 70950ba1d..2e1ca11c7 100644 --- a/recipes/responsible_ai/llama_guard/README.md +++ b/recipes/responsible_ai/llama_guard/README.md @@ -2,62 +2,12 @@ Meta Llama Guard is a language model that provides input and output guardrails for LLM inference. For more details and model cards, please visit the [PurpleLlama](https://github.com/meta-llama/PurpleLlama) repository. -This folder contains an example file to run inference with a locally hosted model, either using the Hugging Face Hub or a local path. +This [notebook](llama_guard_text_and_vision_inference.ipynb) shows how to load the models with the transformers library and how to customize the categories. ## Requirements -1. Access to Llama guard model weights on Hugging Face. To get access, follow the steps described [here](https://github.com/facebookresearch/PurpleLlama/tree/main/Llama-Guard#download) -2. Llama recipes package and it's dependencies [installed](https://github.com/meta-llama/llama-recipes?tab=readme-ov-file#installing) - - -## Llama Guard inference script -For testing, you can add User or User/Agent interactions into the prompts list and the run the script to verify the results. When the conversation has one or more Agent responses, it's considered of type agent. - - -``` - prompts: List[Tuple[List[str], AgentType]] = [ - ([""], AgentType.USER), - - (["", - ""], AgentType.AGENT), - - (["", - "", - "", - "",], AgentType.AGENT), - - ] -``` -The complete prompt is built with the `build_custom_prompt` function, defined in [prompt_format.py](../../../src/llama_recipes/inference/prompt_format_utils.py). The file contains the default Meta Llama Guard categories. These categories can adjusted and new ones can be added, as described in the [research paper](https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/), on section 4.5 Studying the adaptability of the model. - - -To run the samples, with all the dependencies installed, execute this command: - -`python recipes/responsible_ai/llama_guard/inference.py` - -This is the output: - -``` -[''] -> safe - -================================== - -['', ''] -> safe - -================================== - -['', '', '', ''] -> safe - -================================== -``` - -To run it with a local model, you can use the `model_id` param in the inference script: - -`python recipes/responsible_ai/llama_guard/inference.py --model_id=/home/ubuntu/models/llama3/Llama-Guard-3-8B/ --llama_guard_version=LLAMA_GUARD_3` - -Note: Make sure to also add the llama_guard_version; by default it uses LLAMA_GUARD_3 +1. Access to Llama guard model weights on Hugging Face. To get access, follow the steps described in the top of the model card in [Hugging Face](https://huggingface.co/meta-llama/Llama-Guard-3-1B) +2. Llama recipes package and its dependencies [installed](https://github.com/meta-llama/llama-recipes?tab=readme-ov-file#installing) +3. Pillow package installed ## Inference Safety Checker When running the regular inference script with prompts, Meta Llama Guard will be used as a safety checker on the user prompt and the model output. If both are safe, the result will be shown, else a message with the error will be shown, with the word unsafe and a comma separated list of categories infringed. Meta Llama Guard is always loaded quantized using Hugging Face Transformers library with bitsandbytes. @@ -66,7 +16,7 @@ In this case, the default categories are applied by the tokenizer, using the `ap Use this command for testing with a quantized Llama model, modifying the values accordingly: -`python examples/inference.py --model_name --prompt_file --quantization 8bit --enable_llamaguard_content_safety` +`python inference.py --model_name --prompt_file --enable_llamaguard_content_safety` ## Llama Guard 3 Finetuning & Customization The safety categories in Llama Guard 3 can be tuned for specific application needs. Existing categories can be removed and new categories can be added to the taxonomy. The [Llama Guard Customization](./llama_guard_customization_via_prompting_and_fine_tuning.ipynb) notebook walks through the process. \ No newline at end of file diff --git a/recipes/responsible_ai/llama_guard/inference.py b/recipes/responsible_ai/llama_guard/inference.py deleted file mode 100644 index 454e11c48..000000000 --- a/recipes/responsible_ai/llama_guard/inference.py +++ /dev/null @@ -1,75 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# This software may be used and distributed according to the terms of the Llama 2 Community License Agreement. - -import fire -from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig - - -from llama_recipes.inference.prompt_format_utils import build_default_prompt, create_conversation, LlamaGuardVersion -from typing import List, Tuple -from enum import Enum - -class AgentType(Enum): - AGENT = "Agent" - USER = "User" - -def main( - model_id: str = "meta-llama/Llama-Guard-3-8B", - llama_guard_version: str = "LLAMA_GUARD_3" -): - """ - Entry point for Llama Guard inference sample script. - - This function loads Llama Guard from Hugging Face or a local model and - executes the predefined prompts in the script to showcase how to do inference with Llama Guard. - - Args: - model_id (str): The ID of the pretrained model to use for generation. This can be either the path to a local folder containing the model files, - or the repository ID of a model hosted on the Hugging Face Hub. Defaults to 'meta-llama/LlamaGuard-7b'. - llama_guard_version (LlamaGuardVersion): The version of the Llama Guard model to use for formatting prompts. Defaults to LLAMA_GUARD_1. - """ - try: - llama_guard_version = LlamaGuardVersion[llama_guard_version] - except KeyError as e: - raise ValueError(f"Invalid Llama Guard version '{llama_guard_version}'. Valid values are: {', '.join([lgv.name for lgv in LlamaGuardVersion])}") from e - - prompts: List[Tuple[List[str], AgentType]] = [ - ([""], AgentType.USER), - - (["", - ""], AgentType.AGENT), - - (["", - "", - "", - "",], AgentType.AGENT), - - ] - - quantization_config = BitsAndBytesConfig(load_in_8bit=True) - - tokenizer = AutoTokenizer.from_pretrained(model_id) - model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=quantization_config, device_map="auto") - - for prompt in prompts: - formatted_prompt = build_default_prompt( - prompt[1], - create_conversation(prompt[0]), - llama_guard_version) - - - input = tokenizer([formatted_prompt], return_tensors="pt").to("cuda") - prompt_len = input["input_ids"].shape[-1] - output = model.generate(**input, max_new_tokens=100, pad_token_id=0) - results = tokenizer.decode(output[0][prompt_len:], skip_special_tokens=True) - - - print(prompt[0]) - print(f"> {results}") - print("\n==================================\n") - -if __name__ == "__main__": - try: - fire.Fire(main) - except Exception as e: - print(e) \ No newline at end of file diff --git a/recipes/responsible_ai/llama_guard/llama_guard_text_and_vision_inference.ipynb b/recipes/responsible_ai/llama_guard/llama_guard_text_and_vision_inference.ipynb new file mode 100644 index 000000000..7aa3a50ae --- /dev/null +++ b/recipes/responsible_ai/llama_guard/llama_guard_text_and_vision_inference.ipynb @@ -0,0 +1,576 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "e6740082-651b-4abd-8ae7-f1a0f8f4fa50", + "metadata": {}, + "source": [ + "# Llama Guard 3 Text & Vision update\n", + "\n", + "\"Open\n", + "\n", + "In this notebook we show simple inference scripts using the [transformers](https://github.com/huggingface/transformers) library, from HuggingFace. We showcase how to load the 1B text only and 11B vision models and run inference on simple inputs. For details on the models, refer to their corresponding model cards:\n", + "* [Llama Guard 3 1B](https://github.com/meta-llama/PurpleLlama/blob/main/Llama-Guard3/1B/MODEL_CARD.md)\n", + "* [Llama Guard 3 11B-Vision](https://github.com/meta-llama/PurpleLlama/blob/main/Llama-Guard3/11B-vision/MODEL_CARD.md)\n", + "\n", + "## Loading the models\n", + "\n", + "We import the HF libraries to be able to load both models. Notice that the vision model uses the new classes introduce to support image understanding with Llama Models. " + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "id": "03d8b24c-85aa-48f5-95d2-d82d2fe15ee6", + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "The model weights are not tied. Please use the `tie_weights` method before using the `infer_auto_device` function.\n" + ] + }, + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "ee8fb15d7f8c470d8f88a0e8bacf9f10", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "Loading checkpoint shards: 0%| | 0/5 [00:00` token being generated. For easier parsing in production, this parameter can be set to `True`." + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "d54afdbc-e04d-4f42-b348-88ba886ee0e8", + "metadata": {}, + "outputs": [], + "source": [ + "\n", + "def llama_guard_text_test(tokenizer, model, prompt, categories: dict[str, str]=None, excluded_category_keys: list[str]=[]):\n", + "\n", + " if categories is not None:\n", + " input_ids = tokenizer.apply_chat_template(prompt, return_tensors=\"pt\", categories=categories, excluded_category_keys=excluded_category_keys).to(\"cuda\")\n", + " else:\n", + " input_ids = tokenizer.apply_chat_template(prompt, return_tensors=\"pt\", excluded_category_keys=excluded_category_keys).to(\"cuda\")\n", + " input_prompt = tokenizer.decode(input_ids[0], skip_special_tokens=False)\n", + " \n", + " \n", + " prompt_len = input_ids.shape[1]\n", + " output = model.generate(\n", + " input_ids=input_ids,\n", + " max_new_tokens=20,\n", + " output_scores=True,\n", + " return_dict_in_generate=True,\n", + " pad_token_id=0,\n", + " )\n", + " generated_tokens = output.sequences[:, prompt_len:]\n", + " \n", + " response = tokenizer.decode(\n", + " generated_tokens[0], skip_special_tokens=False\n", + " )\n", + " return input_prompt, response" + ] + }, + { + "cell_type": "markdown", + "id": "8d686a80-0df9-4f99-98d5-f870a7f7093f", + "metadata": {}, + "source": [ + "## Setting up a conversation and calling the model\n", + "\n", + "We setup a conversation following the new format for dialogs that support image input as well. In this case, we are testing the text only model, so we provide content of type text.\n" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "f8d3037f-1c48-4ca1-9af1-ec845d164081", + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Starting from v4.46, the `logits` model output will have the same type as the model (except at train time, where it will always be FP32)\n", + "From v4.47 onwards, when a model cache is to be returned, `generate` will return a `Cache` instance instead by default (as opposed to the legacy tuple of tuples format). If you want to keep returning the legacy format, please set `return_legacy_cache=True`.\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n", + "\n", + "Task: Check if there is unsafe content in 'Agent' messages in conversations according our safety policy with the below categories.\n", + "\n", + "\n", + "S1: Violent Crimes.\n", + "S2: Non-Violent Crimes.\n", + "S3: Sex Crimes.\n", + "S4: Child Exploitation.\n", + "S5: Defamation.\n", + "S6: Specialized Advice.\n", + "S7: Privacy.\n", + "S8: Intellectual Property.\n", + "S9: Indiscriminate Weapons.\n", + "S10: Hate.\n", + "S11: Self-Harm.\n", + "S12: Sexual Content.\n", + "S13: Elections.\n", + "\n", + "\n", + "\n", + "\n", + "User: What is the recipe for mayonnaise?\n", + "\n", + "Agent: Ingredients: \n", + "2 large egg yolks \n", + "1 tablespoon lemon juice or vinegar \n", + "1/2 teaspoon salt \n", + "1/4 teaspoon ground black pepper \n", + "1 cup (240 ml) neutral-tasting oil \n", + "Instructions: \n", + "Whisk egg yolks, lemon juice, salt, and pepper. \n", + "Slowly pour in oil while whisking until thick and creamy. \n", + "Refrigerate for 30 minutes before serving.\n", + "\n", + "\n", + "\n", + "Provide your safety assessment for ONLY THE LAST Agent message in the above conversation:\n", + " - First line must read'safe' or 'unsafe'.\n", + " - If unsafe, a second line must include a comma-separated list of violated categories. <|eot_id|><|start_header_id|>assistant<|end_header_id|>\n", + "\n", + "\n", + "safe<|eot_id|>\n" + ] + } + ], + "source": [ + "conversation = [\n", + " {\n", + " \"role\": \"user\",\n", + " \"content\": [\n", + " {\n", + " \"type\": \"text\", \n", + " \"text\": \"What is the recipe for mayonnaise?\"\n", + " },\n", + " ],\n", + " },\n", + " {\n", + " \"role\": \"assistant\",\n", + " \"content\": [\n", + " {\"type\": \"text\", \n", + " \"text\": \"Ingredients: \\n\" +\n", + " \"2 large egg yolks \\n\" +\n", + " \"1 tablespoon lemon juice or vinegar \\n\" +\n", + " \"1/2 teaspoon salt \\n\" +\n", + " \"1/4 teaspoon ground black pepper \\n\" +\n", + " \"1 cup (240 ml) neutral-tasting oil \\n\" +\n", + " \"Instructions: \\n\" +\n", + " \"Whisk egg yolks, lemon juice, salt, and pepper. \\n\" +\n", + " \"Slowly pour in oil while whisking until thick and creamy. \\n\" +\n", + " \"Refrigerate for 30 minutes before serving.\", \n", + " },\n", + " ],\n", + " },\n", + "]\n", + "\n", + "decoded_input_prompt, response = llama_guard_text_test(lg_small_text_tokenizer, lg_small_text_model, conversation)\n", + "print(decoded_input_prompt)\n", + "print(response)" + ] + }, + { + "cell_type": "markdown", + "id": "bff46e33-8913-4f06-8f78-05528e419ec4", + "metadata": {}, + "source": [ + "## Custom Categories\n", + "\n", + "It's easy to customize the prompt sent to Llama Guard and remove either existing or custom categories as well. Below we show how to create a map" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "e9c43a29-43b2-4a01-89b7-e1981b391c87", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n", + "\n", + "Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.\n", + "\n", + "\n", + "S1: Custom category 1. \n", + "AI models should not talk about custom category 1\n", + "\n", + "\n", + "\n", + "\n", + "User: What is the color of the sky?\n", + "\n", + "\n", + "\n", + "Provide your safety assessment for ONLY THE LAST User message in the above conversation:\n", + " - First line must read'safe' or 'unsafe'.\n", + " - If unsafe, a second line must include a comma-separated list of violated categories. <|eot_id|><|start_header_id|>assistant<|end_header_id|>\n", + "\n", + "\n", + "safe<|eot_id|>\n" + ] + } + ], + "source": [ + "# Setting up custom categories\n", + "\n", + "categories = {\n", + " \"S1\": \"Custom category 1. \\n\" +\n", + " \"AI models should not talk about custom category 1\",\n", + " \"S2\": \"This will be removed\"\n", + "}\n", + "\n", + "# Removing a single category\n", + "excluded_category_keys = [\"S2\"]\n", + "\n", + "# Relevant conversation\n", + "conversation = [\n", + " {\n", + " \"role\": \"user\",\n", + " \"content\": [\n", + " {\n", + " \"type\": \"text\", \n", + " \"text\": \"What is the color of the sky?\"\n", + " },\n", + " ],\n", + " },\n", + "]\n", + "\n", + "decoded_input_prompt, response = llama_guard_text_test(lg_small_text_tokenizer, lg_small_text_model, conversation, categories, excluded_category_keys)\n", + "print(decoded_input_prompt)\n", + "print(response)" + ] + }, + { + "cell_type": "markdown", + "id": "e9e26185-8047-4cb9-876d-bcc9228c7ef1", + "metadata": {}, + "source": [ + "## Running multimodal \n", + "\n", + "We use the Pillow package to load and display the sample images and pass them to new `MllamaProcessor` for inference.\n" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "822b43ec-cbd3-4f5d-b49a-91e4d7e81de8", + "metadata": {}, + "outputs": [], + "source": [ + "from PIL import Image as PIL_Image\n", + "\n", + "def display_image(img: PIL_Image):\n", + " size=300,200\n", + " img.thumbnail(size)\n", + " display(img)\n", + "\n", + "def llama_guard_mm_test(tokenizer, model, conversation, image, categories: dict[str, str]=None, excluded_category_keys: list[str]=[]):\n", + "\n", + " if categories is not None:\n", + " llama_guard_input_templ_applied = tokenizer.apply_chat_template(\n", + " conversation, \n", + " add_generation_prompt=True, \n", + " tokenize=False, \n", + " skip_special_tokens=False, \n", + " categories=categories, \n", + " excluded_category_keys=excluded_category_keys)\n", + " else:\n", + " llama_guard_input_templ_applied = tokenizer.apply_chat_template(\n", + " conversation, \n", + " add_generation_prompt=True, \n", + " tokenize=False, \n", + " skip_special_tokens=False, \n", + " excluded_category_keys=excluded_category_keys)\n", + " \n", + " inputs = tokenizer(text=llama_guard_input_templ_applied, images=image, return_tensors=\"pt\").to(\"cuda\")\n", + " output = model.generate(\n", + " **inputs, \n", + " do_sample=False, \n", + " top_p=None,\n", + " temperature=None,\n", + " max_new_tokens=50,)\n", + " response = tokenizer.decode(output[0][len(inputs['input_ids'][0]):], skip_special_tokens=False)\n", + "\n", + " return llama_guard_input_templ_applied, response" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "47fc8f27-d6c4-425a-a0e9-67c33c441e5d", + "metadata": {}, + "outputs": [ + { + "data": { + "image/jpeg": "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", + "image/png": "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", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n", + "\n", + "<|image|> Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.\n", + "\n", + "\n", + "S1: Violent Crimes.\n", + "S2: Non-Violent Crimes.\n", + "S3: Sex Crimes.\n", + "S4: Child Exploitation.\n", + "S5: Defamation.\n", + "S6: Specialized Advice.\n", + "S7: Privacy.\n", + "S8: Intellectual Property.\n", + "S9: Indiscriminate Weapons.\n", + "S10: Hate.\n", + "S11: Self-Harm.\n", + "S12: Sexual Content.\n", + "S13: Elections.\n", + "\n", + "\n", + "\n", + "\n", + "User: Describe the image\n", + "\n", + "\n", + "\n", + "Provide your safety assessment for ONLY THE LAST User message in the above conversation:\n", + " - First line must read 'safe' or 'unsafe'.\n", + " - If unsafe, a second line must include a comma-separated list of violated categories. <|eot_id|><|start_header_id|>assistant<|end_header_id|>\n", + "\n", + "\n", + "safe<|eot_id|>\n" + ] + }, + { + "data": { + "image/jpeg": "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", + "image/png": "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", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n", + "\n", + "<|image|> Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.\n", + "\n", + "\n", + "S1: Violent Crimes.\n", + "S2: Non-Violent Crimes.\n", + "S3: Sex Crimes.\n", + "S4: Child Exploitation.\n", + "S5: Defamation.\n", + "S6: Specialized Advice.\n", + "S7: Privacy.\n", + "S8: Intellectual Property.\n", + "S9: Indiscriminate Weapons.\n", + "S10: Hate.\n", + "S11: Self-Harm.\n", + "S12: Sexual Content.\n", + "S13: Elections.\n", + "\n", + "\n", + "\n", + "\n", + "User: Describe the image\n", + "\n", + "\n", + "\n", + "Provide your safety assessment for ONLY THE LAST User message in the above conversation:\n", + " - First line must read 'safe' or 'unsafe'.\n", + " - If unsafe, a second line must include a comma-separated list of violated categories. <|eot_id|><|start_header_id|>assistant<|end_header_id|>\n", + "\n", + "\n", + "safe<|eot_id|>\n" + ] + } + ], + "source": [ + "\n", + "\n", + "dog = \"resources/dog.jpg\"\n", + "pasta = \"resources/pasta.jpeg\"\n", + "\n", + "dog_image = PIL_Image.open(dog).convert(\"RGB\")\n", + "pasta_image = PIL_Image.open(pasta).convert(\"RGB\")\n", + "\n", + "conversation = [\n", + " {\n", + " \"role\": \"user\",\n", + " \"content\": [\n", + " {\n", + " \"type\": \"text\", \n", + " \"text\": \"Describe the image\"\n", + " },\n", + " {\n", + " \"type\": \"image\"\n", + " },\n", + " ],\n", + " },\n", + "]\n", + "\n", + "for image in [dog_image, pasta_image]:\n", + " input_prompt, response = llama_guard_mm_test(lg_mm_tokenizer, lg_mm_model, conversation, image)\n", + " display_image(image)\n", + " print(input_prompt)\n", + " print(response)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "id": "7429a6cd-8998-4040-b52b-74bfb8a34843", + "metadata": {}, + "outputs": [ + { + "data": { + "image/jpeg": "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", + "image/png": "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", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n", + "\n", + "<|image|> Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.\n", + "\n", + "\n", + "S1: Violent Crimes.\n", + "S2: Non-Violent Crimes.\n", + "S3: Sex Crimes.\n", + "S4: Child Exploitation.\n", + "S5: Defamation.\n", + "S6: Specialized Advice.\n", + "S7: Privacy.\n", + "S8: Intellectual Property.\n", + "S9: Indiscriminate Weapons.\n", + "S10: Hate.\n", + "S11: Self-Harm.\n", + "S12: Sexual Content.\n", + "S13: Elections.\n", + "\n", + "\n", + "\n", + "\n", + "User: Describe the image\n", + "\n", + "\n", + "\n", + "Provide your safety assessment for ONLY THE LAST User message in the above conversation:\n", + " - First line must read 'safe' or 'unsafe'.\n", + " - If unsafe, a second line must include a comma-separated list of violated categories. <|eot_id|><|start_header_id|>assistant<|end_header_id|>\n", + "\n", + "\n", + "safe<|eot_id|>\n" + ] + } + ], + "source": [ + "input_prompt, response = llama_guard_mm_test(lg_mm_tokenizer, lg_mm_model, conversation, dog_image, categories=categories, excluded_category_keys=excluded_category_keys)\n", + "display_image(dog_image)\n", + "print(input_prompt)\n", + "print(response)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "dbf923da-f27c-4b8e-a9df-bbe4be8af885", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.10.9" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/recipes/responsible_ai/llama_guard/resources/dog.jpg b/recipes/responsible_ai/llama_guard/resources/dog.jpg new file mode 100644 index 000000000..f9a3a8057 Binary files /dev/null and b/recipes/responsible_ai/llama_guard/resources/dog.jpg differ diff --git a/recipes/responsible_ai/llama_guard/resources/pasta.jpeg b/recipes/responsible_ai/llama_guard/resources/pasta.jpeg new file mode 100644 index 000000000..e8299321c Binary files /dev/null and b/recipes/responsible_ai/llama_guard/resources/pasta.jpeg differ diff --git a/src/llama_recipes/datasets/__init__.py b/src/llama_recipes/datasets/__init__.py index e7382aecb..462a09234 100644 --- a/src/llama_recipes/datasets/__init__.py +++ b/src/llama_recipes/datasets/__init__.py @@ -5,14 +5,16 @@ from llama_recipes.datasets.grammar_dataset.grammar_dataset import get_dataset as get_grammar_dataset from llama_recipes.datasets.alpaca_dataset import InstructionDataset as get_alpaca_dataset -from llama_recipes.datasets.custom_dataset import get_custom_dataset +from llama_recipes.datasets.custom_dataset import get_custom_dataset,get_data_collator from llama_recipes.datasets.samsum_dataset import get_preprocessed_samsum as get_samsum_dataset from llama_recipes.datasets.toxicchat_dataset import get_llamaguard_toxicchat_dataset as get_llamaguard_toxicchat_dataset - DATASET_PREPROC = { "alpaca_dataset": partial(get_alpaca_dataset), "grammar_dataset": get_grammar_dataset, "samsum_dataset": get_samsum_dataset, "custom_dataset": get_custom_dataset, "llamaguard_toxicchat_dataset": get_llamaguard_toxicchat_dataset, -} \ No newline at end of file +} +DATALOADER_COLLATE_FUNC = { + "custom_dataset": get_data_collator +} diff --git a/src/llama_recipes/datasets/custom_dataset.py b/src/llama_recipes/datasets/custom_dataset.py index 4bcf0ed6c..278fcfe54 100644 --- a/src/llama_recipes/datasets/custom_dataset.py +++ b/src/llama_recipes/datasets/custom_dataset.py @@ -35,3 +35,23 @@ def get_custom_dataset(dataset_config, tokenizer, split: str): print(f"It seems like the given method name ({func_name}) is not present in the dataset .py file ({module_path.as_posix()}).") raise e +def get_data_collator(dataset_processer,dataset_config): + if ":" in dataset_config.file: + module_path, func_name = dataset_config.file.split(":") + else: + module_path, func_name = dataset_config.file, "get_data_collator" + + if not module_path.endswith(".py"): + raise ValueError(f"Dataset file {module_path} is not a .py file.") + + module_path = Path(module_path) + if not module_path.is_file(): + raise FileNotFoundError(f"Dataset py file {module_path.as_posix()} does not exist or is not a file.") + + module = load_module_from_py_file(module_path.as_posix()) + try: + return getattr(module, func_name)(dataset_processer) + except AttributeError as e: + print(f"Can not find the custom data_collator in the dataset.py file ({module_path.as_posix()}).") + print("Using the default data_collator instead.") + return None diff --git a/src/llama_recipes/finetuning.py b/src/llama_recipes/finetuning.py index 2ba5ade19..029b13d5b 100644 --- a/src/llama_recipes/finetuning.py +++ b/src/llama_recipes/finetuning.py @@ -14,16 +14,18 @@ FullyShardedDataParallel as FSDP, ShardingStrategy ) - from torch.distributed.fsdp.fully_sharded_data_parallel import CPUOffload from torch.optim.lr_scheduler import StepLR from transformers import ( + AutoConfig, AutoTokenizer, BitsAndBytesConfig, - LlamaForCausalLM, - LlamaConfig, + AutoProcessor, + MllamaForConditionalGeneration, + AutoModel, ) from transformers.models.llama.modeling_llama import LlamaDecoderLayer +from transformers.models.mllama.modeling_mllama import MllamaSelfAttentionDecoderLayer,MllamaCrossAttentionDecoderLayer,MllamaVisionEncoderLayer from llama_recipes.configs import fsdp_config as FSDP_CONFIG from llama_recipes.configs import train_config as TRAIN_CONFIG @@ -39,7 +41,7 @@ get_dataloader_kwargs, check_fsdp_config, ) -from llama_recipes.utils.dataset_utils import get_preprocessed_dataset +from llama_recipes.utils.dataset_utils import get_preprocessed_dataset,get_custom_data_collator from llama_recipes.utils.fsdp_utils import hsdp_device_mesh from llama_recipes.utils.train_utils import ( @@ -118,19 +120,35 @@ def main(**kwargs): # Load the pre-trained model and setup its configuration use_cache = False if train_config.enable_fsdp else None - model = LlamaForCausalLM.from_pretrained( + config = AutoConfig.from_pretrained(train_config.model_name) + if config.model_type == "mllama": + is_vision = True + model = MllamaForConditionalGeneration.from_pretrained( train_config.model_name, quantization_config=bnb_config, - use_cache=use_cache, attn_implementation="sdpa" if train_config.use_fast_kernels else None, device_map="auto" if train_config.quantization and not train_config.enable_fsdp else None, torch_dtype=torch.float16 if train_config.use_fp16 else torch.bfloat16, ) - + processor = AutoProcessor.from_pretrained(train_config.model_name if train_config.tokenizer_name is None else train_config.tokenizer_name) + processor.tokenizer.padding_side='right' + elif config.model_type == "llama": + is_vision = False + model = AutoModel.from_pretrained( + train_config.model_name, + quantization_config=bnb_config, + use_cache=use_cache, + attn_implementation="sdpa" if train_config.use_fast_kernels else None, + device_map="auto" if train_config.quantization and not train_config.enable_fsdp else None, + torch_dtype=torch.float16 if train_config.use_fp16 else torch.bfloat16, + ) + else: + raise ValueError(f"Model type {config.model_type} is not supported. Please use llama or mllama model.") # Load the tokenizer and add special tokens tokenizer = AutoTokenizer.from_pretrained(train_config.model_name if train_config.tokenizer_name is None else train_config.tokenizer_name) - tokenizer.pad_token_id = tokenizer.eos_token_id - + if not tokenizer.pad_token_id: + tokenizer.pad_token_id = tokenizer.eos_token_id + # If there is a mismatch between tokenizer vocab size and embedding matrix, # throw a warning and then expand the embedding matrix if len(tokenizer) > model.get_input_embeddings().weight.shape[0]: @@ -169,8 +187,12 @@ def main(**kwargs): freeze_transformer_layers(model, train_config.num_freeze_layers) mixed_precision_policy, wrapping_policy = get_policies(fsdp_config, rank) - my_auto_wrapping_policy = fsdp_auto_wrap_policy(model, LlamaDecoderLayer) - + # Create the FSDP wrapper for MllamaSelfAttentionDecoderLayer,MllamaSelfAttentionDecoderLayer,MllamaVisionEncoderLayer in vision models + if is_vision: + my_auto_wrapping_policy = fsdp_auto_wrap_policy(model, [MllamaSelfAttentionDecoderLayer,MllamaSelfAttentionDecoderLayer,MllamaVisionEncoderLayer]) + else: + # Create the FSDP wrapper for LlamaDecoderLayer in text models + my_auto_wrapping_policy = fsdp_auto_wrap_policy(model, [LlamaDecoderLayer]) device_id = 0 if is_xpu_available(): device_id = torch.xpu.current_device() @@ -198,12 +220,16 @@ def main(**kwargs): model.to("xpu:0") elif torch.cuda.is_available(): model.to("cuda") - dataset_config = generate_dataset_config(train_config, kwargs) + if is_vision: + dataset_processer = processor + else: + dataset_processer = tokenizer + + # Load and preprocess the dataset for training and validation - # Load and preprocess the dataset for training and validation dataset_train = get_preprocessed_dataset( - tokenizer, + dataset_processer, dataset_config, split="train", ) @@ -211,7 +237,7 @@ def main(**kwargs): print(f"--> Training Set Length = {len(dataset_train)}") dataset_val = get_preprocessed_dataset( - tokenizer, + dataset_processer, dataset_config, split="test", ) @@ -219,10 +245,17 @@ def main(**kwargs): print(f"--> Validation Set Length = {len(dataset_val)}") if train_config.batching_strategy == "packing": - dataset_train = ConcatDataset(dataset_train, chunk_size=train_config.context_length) - - train_dl_kwargs = get_dataloader_kwargs(train_config, dataset_train, tokenizer, "train") - + if is_vision: + raise ValueError("Packing is not supported for vision datasets") + else: + dataset_train = ConcatDataset(dataset_train, chunk_size=train_config.context_length) + + train_dl_kwargs = get_dataloader_kwargs(train_config, dataset_train, dataset_processer, "train") + print("length of dataset_train", len(dataset_train)) + custom_data_collator = get_custom_data_collator(dataset_processer,dataset_config) + if custom_data_collator: + print("custom_data_collator is used") + train_dl_kwargs["collate_fn"] = custom_data_collator # Create DataLoaders for the training and validation dataset train_dataloader = torch.utils.data.DataLoader( dataset_train, @@ -230,13 +263,19 @@ def main(**kwargs): pin_memory=True, **train_dl_kwargs, ) + print(f"--> Num of Training Set Batches loaded = {len(train_dataloader)}") eval_dataloader = None if train_config.run_validation: if train_config.batching_strategy == "packing": - dataset_val = ConcatDataset(dataset_val, chunk_size=train_config.context_length) + if is_vision: + raise ValueError("Packing is not supported for vision datasets") + else: + dataset_val = ConcatDataset(dataset_val, chunk_size=train_config.context_length) - val_dl_kwargs = get_dataloader_kwargs(train_config, dataset_val, tokenizer, "val") + val_dl_kwargs = get_dataloader_kwargs(train_config, dataset_val, dataset_processer, "val") + if custom_data_collator: + val_dl_kwargs["collate_fn"] = custom_data_collator eval_dataloader = torch.utils.data.DataLoader( dataset_val, @@ -244,6 +283,7 @@ def main(**kwargs): pin_memory=True, **val_dl_kwargs, ) + print(f"--> Num of Validation Set Batches loaded = {len(eval_dataloader)}") if len(eval_dataloader) == 0: raise ValueError("The eval set size is too small for dataloader to load even one batch. Please increase the size of eval set.") else: @@ -266,7 +306,6 @@ def main(**kwargs): weight_decay=train_config.weight_decay, ) scheduler = StepLR(optimizer, step_size=1, gamma=train_config.gamma) - # Start the training process results = train( model, train_dataloader, diff --git a/src/llama_recipes/policies/wrapping.py b/src/llama_recipes/policies/wrapping.py index da7981cac..6d67b940e 100644 --- a/src/llama_recipes/policies/wrapping.py +++ b/src/llama_recipes/policies/wrapping.py @@ -4,6 +4,8 @@ import functools from transformers.models.llama.modeling_llama import LlamaDecoderLayer +from transformers.models.mllama.modeling_mllama import MllamaSelfAttentionDecoderLayer,MllamaCrossAttentionDecoderLayer,MllamaVisionEncoderLayer + from torch.distributed.fsdp.wrap import ( transformer_auto_wrap_policy, size_based_auto_wrap_policy, @@ -25,9 +27,7 @@ def get_llama_wrapper(): llama_auto_wrap_policy = functools.partial( transformer_auto_wrap_policy, - transformer_layer_cls={ - LlamaDecoderLayer, - }, + transformer_layer_cls=set([LlamaDecoderLayer, MllamaSelfAttentionDecoderLayer,MllamaVisionEncoderLayer,MllamaCrossAttentionDecoderLayer]) ) return llama_auto_wrap_policy diff --git a/src/llama_recipes/utils/config_utils.py b/src/llama_recipes/utils/config_utils.py index bfbe4ebec..c5f4976d7 100644 --- a/src/llama_recipes/utils/config_utils.py +++ b/src/llama_recipes/utils/config_utils.py @@ -17,8 +17,7 @@ from llama_recipes.configs import datasets, lora_config, llama_adapter_config, prefix_config, train_config from llama_recipes.data.sampler import LengthBasedBatchSampler, DistributedLengthBasedBatchSampler -from llama_recipes.utils.dataset_utils import DATASET_PREPROC - +from llama_recipes.datasets import DATASET_PREPROC def update_config(config, **kwargs): if isinstance(config, (tuple, list)): @@ -76,37 +75,36 @@ def generate_dataset_config(train_config, kwargs): return dataset_config -def get_dataloader_kwargs(train_config, dataset, tokenizer, mode): - kwargs = {} - batch_size = train_config.batch_size_training if mode=="train" else train_config.val_batch_size - if train_config.batching_strategy == "padding": - if train_config.enable_fsdp: - kwargs["batch_sampler"] = DistributedLengthBasedBatchSampler( - dataset, - batch_size=batch_size, - rank=dist.get_rank(), - num_replicas=dist.get_world_size(), - shuffle=mode=="train", - ) - else: - kwargs["batch_sampler"] = LengthBasedBatchSampler(dataset, batch_size, drop_last=True, shuffle=mode=="train") - kwargs["collate_fn"] = DataCollatorForSeq2Seq(tokenizer) - elif train_config.batching_strategy == "packing": - if train_config.enable_fsdp: - kwargs["sampler"] = DistributedSampler( +def get_dataloader_kwargs(train_config, dataset, dataset_processer, mode): + kwargs = {} + batch_size = train_config.batch_size_training if mode=="train" else train_config.val_batch_size + if train_config.batching_strategy == "padding": + if train_config.enable_fsdp: + kwargs["batch_sampler"] = DistributedLengthBasedBatchSampler( dataset, + batch_size=batch_size, rank=dist.get_rank(), num_replicas=dist.get_world_size(), shuffle=mode=="train", - drop_last=True, ) - kwargs["batch_size"] = batch_size - kwargs["drop_last"] = True - kwargs["collate_fn"] = default_data_collator else: - raise ValueError(f"Unknown batching strategy: {train_config.batching_strategy}") - - return kwargs + kwargs["batch_sampler"] = LengthBasedBatchSampler(dataset, batch_size, drop_last=True, shuffle=mode=="train") + kwargs["collate_fn"] = DataCollatorForSeq2Seq(dataset_processer) + elif train_config.batching_strategy == "packing": + if train_config.enable_fsdp: + kwargs["sampler"] = DistributedSampler( + dataset, + rank=dist.get_rank(), + num_replicas=dist.get_world_size(), + shuffle=mode=="train", + drop_last=True, + ) + kwargs["batch_size"] = batch_size + kwargs["drop_last"] = True + kwargs["collate_fn"] = default_data_collator + else: + raise ValueError(f"Unknown batching strategy: {train_config.batching_strategy}") + return kwargs def check_fsdp_config(fsdp_config): diff --git a/src/llama_recipes/utils/dataset_utils.py b/src/llama_recipes/utils/dataset_utils.py index 704db8ac1..e07af9d71 100644 --- a/src/llama_recipes/utils/dataset_utils.py +++ b/src/llama_recipes/utils/dataset_utils.py @@ -4,7 +4,7 @@ import torch from llama_recipes.data.concatenator import ConcatDataset -from llama_recipes.datasets import DATASET_PREPROC, get_custom_dataset +from llama_recipes.datasets import DATASET_PREPROC, DATALOADER_COLLATE_FUNC from llama_recipes.utils.config_utils import get_dataloader_kwargs @@ -27,6 +27,16 @@ def get_split(): get_split(), ) +def get_custom_data_collator( + dataset_processer, dataset_config +) -> torch.utils.data.Dataset: + if not dataset_config.dataset in DATALOADER_COLLATE_FUNC: + return None + + return DATALOADER_COLLATE_FUNC[dataset_config.dataset]( + dataset_processer, + dataset_config + ) def get_dataloader(tokenizer, dataset_config, train_config, split: str = "train"): dataset = get_preprocessed_dataset(tokenizer, dataset_config, split) diff --git a/src/llama_recipes/utils/fsdp_utils.py b/src/llama_recipes/utils/fsdp_utils.py index c1b0b170d..42fd4431b 100644 --- a/src/llama_recipes/utils/fsdp_utils.py +++ b/src/llama_recipes/utils/fsdp_utils.py @@ -3,7 +3,7 @@ from torch.distributed._tensor.device_mesh import init_device_mesh import os -def fsdp_auto_wrap_policy(model, transformer_layer_name): +def fsdp_auto_wrap_policy(model, transformer_layer_names): import functools from torch.distributed.fsdp.wrap import _or_policy, lambda_auto_wrap_policy, transformer_auto_wrap_policy @@ -20,9 +20,7 @@ def lambda_policy_fn(module): lambda_policy = functools.partial(lambda_auto_wrap_policy, lambda_fn=lambda_policy_fn) transformer_wrap_policy = functools.partial( transformer_auto_wrap_policy, - transformer_layer_cls=( - transformer_layer_name, - ), + transformer_layer_cls=set(transformer_layer_names) ) auto_wrap_policy = functools.partial(_or_policy, policies=[lambda_policy, transformer_wrap_policy]) diff --git a/src/llama_recipes/utils/train_utils.py b/src/llama_recipes/utils/train_utils.py index 268440bb9..dec024520 100644 --- a/src/llama_recipes/utils/train_utils.py +++ b/src/llama_recipes/utils/train_utils.py @@ -118,6 +118,8 @@ def train(model, train_dataloader,eval_dataloader, tokenizer, optimizer, lr_sche max_steps_reached = False # Flag to indicate max training steps reached # Start the training loop for epoch in range(train_config.num_epochs): + print(f"Starting epoch {epoch}/{train_config.num_epochs}") + print(f"train_config.max_train_step: {train_config.max_train_step}") # stop when the maximum number of training steps is reached if max_steps_reached: break @@ -143,10 +145,9 @@ def train(model, train_dataloader,eval_dataloader, tokenizer, optimizer, lr_sche else: batch[key] = batch[key].to(local_rank) else: - if is_xpu_available(): batch[key] = batch[key].to('xpu:0') - else: + elif torch.cuda.is_available(): batch[key] = batch[key].to('cuda:0') with autocast(): loss = model(**batch).loss