diff --git a/examples/Getting_to_know_Llama.ipynb b/examples/Getting_to_know_Llama.ipynb
index 265a07915c8f1fcb0feb9bd5268cc92a4f17847b..507bd7065f9c7481123889617397db951033bbdf 100644
--- a/examples/Getting_to_know_Llama.ipynb
+++ b/examples/Getting_to_know_Llama.ipynb
@@ -1 +1 @@
-{"cells":[{"cell_type":"markdown","metadata":{"id":"RJSnI0Xy-kCm"},"source":[""]},{"cell_type":"markdown","metadata":{"id":"LERqQn5v8-ak"},"source":["# **Getting to know Llama 2: Everything you need to start building**\n","Our goal in this session is to provide a guided tour of Llama 2, including understanding different Llama 2 models, how and where to access them, Generative AI and Chatbot architectures, prompt engineering, RAG (Retrieval Augmented Generation), Fine-tuning and more. All this is implemented with a starter code for you to take it and use it in your Llama 2 projects."]},{"cell_type":"markdown","metadata":{"id":"ioVMNcTesSEk"},"source":["##**0 - Prerequisites**\n","* Basic understanding of Large Language Models\n","\n","* Basic understanding of Python"]},{"cell_type":"code","execution_count":5,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["Requirement already satisfied: matplotlib in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (3.8.0)\n","Requirement already satisfied: contourpy>=1.0.1 in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from matplotlib) (1.1.1)\n","Requirement already satisfied: cycler>=0.10 in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from matplotlib) (0.11.0)\n","Requirement already satisfied: fonttools>=4.22.0 in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from matplotlib) (4.42.1)\n","Requirement already satisfied: kiwisolver>=1.0.1 in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from matplotlib) (1.4.5)\n","Requirement already satisfied: numpy<2,>=1.21 in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from matplotlib) (1.25.2)\n","Requirement already satisfied: packaging>=20.0 in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from matplotlib) (23.1)\n","Requirement already satisfied: pillow>=6.2.0 in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from matplotlib) (9.3.0)\n","Requirement already satisfied: pyparsing>=2.3.1 in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from matplotlib) (3.1.1)\n","Requirement already satisfied: python-dateutil>=2.7 in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from matplotlib) (2.8.2)\n","Requirement already satisfied: six>=1.5 in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from python-dateutil>=2.7->matplotlib) (1.16.0)\n","Note: you may need to restart the kernel to use updated packages.\n","Collecting ipywidgets\n"," Obtaining dependency information for ipywidgets from https://files.pythonhosted.org/packages/4a/0e/57ed498fafbc60419a9332d872e929879ceba2d73cb11d284d7112472b3e/ipywidgets-8.1.1-py3-none-any.whl.metadata\n"," Downloading ipywidgets-8.1.1-py3-none-any.whl.metadata (2.4 kB)\n","Requirement already satisfied: comm>=0.1.3 in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from ipywidgets) (0.1.4)\n","Requirement already satisfied: ipython>=6.1.0 in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from ipywidgets) (8.15.0)\n","Requirement already satisfied: traitlets>=4.3.1 in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from ipywidgets) (5.10.0)\n","Collecting widgetsnbextension~=4.0.9 (from ipywidgets)\n"," Obtaining dependency information for widgetsnbextension~=4.0.9 from https://files.pythonhosted.org/packages/29/03/107d96077c4befed191f7ad1a12c7b52a8f9d2778a5836d59f9855c105f6/widgetsnbextension-4.0.9-py3-none-any.whl.metadata\n"," Downloading widgetsnbextension-4.0.9-py3-none-any.whl.metadata (1.6 kB)\n","Collecting jupyterlab-widgets~=3.0.9 (from ipywidgets)\n"," Obtaining dependency information for jupyterlab-widgets~=3.0.9 from https://files.pythonhosted.org/packages/e8/05/0ebab152288693b5ec7b339aab857362947031143b282853b4c2dd4b5b40/jupyterlab_widgets-3.0.9-py3-none-any.whl.metadata\n"," Downloading jupyterlab_widgets-3.0.9-py3-none-any.whl.metadata (4.1 kB)\n","Requirement already satisfied: backcall in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from ipython>=6.1.0->ipywidgets) (0.2.0)\n","Requirement already satisfied: decorator in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from ipython>=6.1.0->ipywidgets) (5.1.1)\n","Requirement already satisfied: jedi>=0.16 in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from ipython>=6.1.0->ipywidgets) (0.19.0)\n","Requirement already satisfied: matplotlib-inline in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from ipython>=6.1.0->ipywidgets) (0.1.6)\n","Requirement already satisfied: pickleshare in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from ipython>=6.1.0->ipywidgets) (0.7.5)\n","Requirement already satisfied: prompt-toolkit!=3.0.37,<3.1.0,>=3.0.30 in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from ipython>=6.1.0->ipywidgets) (3.0.39)\n","Requirement already satisfied: pygments>=2.4.0 in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from ipython>=6.1.0->ipywidgets) (2.16.1)\n","Requirement already satisfied: stack-data in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from ipython>=6.1.0->ipywidgets) (0.6.2)\n","Requirement already satisfied: exceptiongroup in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from ipython>=6.1.0->ipywidgets) (1.1.3)\n","Requirement already satisfied: pexpect>4.3 in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from ipython>=6.1.0->ipywidgets) (4.8.0)\n","Requirement already satisfied: parso<0.9.0,>=0.8.3 in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from jedi>=0.16->ipython>=6.1.0->ipywidgets) (0.8.3)\n","Requirement already satisfied: ptyprocess>=0.5 in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from pexpect>4.3->ipython>=6.1.0->ipywidgets) (0.7.0)\n","Requirement already satisfied: wcwidth in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from prompt-toolkit!=3.0.37,<3.1.0,>=3.0.30->ipython>=6.1.0->ipywidgets) (0.2.6)\n","Requirement already satisfied: executing>=1.2.0 in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from stack-data->ipython>=6.1.0->ipywidgets) (1.2.0)\n","Requirement already satisfied: asttokens>=2.1.0 in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from stack-data->ipython>=6.1.0->ipywidgets) (2.4.0)\n","Requirement already satisfied: pure-eval in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from stack-data->ipython>=6.1.0->ipywidgets) (0.2.2)\n","Requirement already satisfied: six>=1.12.0 in /data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages (from asttokens>=2.1.0->stack-data->ipython>=6.1.0->ipywidgets) (1.16.0)\n","Downloading ipywidgets-8.1.1-py3-none-any.whl (139 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m139.4/139.4 kB\u001b[0m \u001b[31m2.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0mta \u001b[36m0:00:01\u001b[0m\n","\u001b[?25hDownloading jupyterlab_widgets-3.0.9-py3-none-any.whl (214 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m214.9/214.9 kB\u001b[0m \u001b[31m5.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0mta \u001b[36m0:00:01\u001b[0m\n","\u001b[?25hDownloading widgetsnbextension-4.0.9-py3-none-any.whl (2.3 MB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.3/2.3 MB\u001b[0m \u001b[31m24.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m\n","\u001b[?25hInstalling collected packages: widgetsnbextension, jupyterlab-widgets, ipywidgets\n","Successfully installed ipywidgets-8.1.1 jupyterlab-widgets-3.0.9 widgetsnbextension-4.0.9\n","Note: you may need to restart the kernel to use updated packages.\n"]}],"source":["%pip install matplotlib\n","%pip install ipywidgets"]},{"cell_type":"code","execution_count":6,"metadata":{"id":"ktEA7qXmwdUM"},"outputs":[],"source":["# presentation layer code\n","\n","import base64\n","from IPython.display import Image, display\n","import matplotlib.pyplot as plt\n","import ipywidgets as widgets\n","from IPython.display import display, Markdown\n","\n","\n","def mm(graph):\n"," graphbytes = graph.encode(\"ascii\")\n"," base64_bytes = base64.b64encode(graphbytes)\n"," base64_string = base64_bytes.decode(\"ascii\")\n"," display(Image(url=\"https://mermaid.ink/img/\" + base64_string))\n","\n","def genai_app_arch():\n"," mm(\"\"\"\n"," flowchart TD\n"," A[Users] --> B(Applications e.g. mobile, web)\n"," B --> |Hosted API|C(Platforms e.g. Custom, HuggingFace, Replicate)\n"," B -- optional --> E(Frameworks e.g. LangChain)\n"," C-->|User Input|D[Llama 2]\n"," D-->|Model Output|C\n"," E --> C\n"," classDef default fill:#CCE6FF,stroke:#84BCF5,textColor:#1C2B33,fontFamily:trebuchet ms;\n"," \"\"\")\n","\n","def rag_arch():\n"," mm(\"\"\"\n"," flowchart TD\n"," A[User Prompts] --> B(Frameworks e.g. LangChain)\n"," B <--> |Database, Docs, XLS|C[fa:fa-database External Data]\n"," B -->|API|D[Llama 2]\n"," classDef default fill:#CCE6FF,stroke:#84BCF5,textColor:#1C2B33,fontFamily:trebuchet ms;\n"," \"\"\")\n","\n","def llama2_family():\n"," mm(\"\"\"\n"," graph LR;\n"," llama-2 --> llama-2-7b\n"," llama-2 --> llama-2-13b\n"," llama-2 --> llama-2-70b\n"," llama-2-7b --> llama-2-7b-chat\n"," llama-2-13b --> llama-2-13b-chat\n"," llama-2-70b --> llama-2-70b-chat\n"," classDef default fill:#CCE6FF,stroke:#84BCF5,textColor:#1C2B33,fontFamily:trebuchet ms;\n"," \"\"\")\n","\n","def apps_and_llms():\n"," mm(\"\"\"\n"," graph LR;\n"," users --> apps\n"," apps --> frameworks\n"," frameworks --> platforms\n"," platforms --> Llama 2\n"," classDef default fill:#CCE6FF,stroke:#84BCF5,textColor:#1C2B33,fontFamily:trebuchet ms;\n"," \"\"\")\n","\n","\n","\n","# Create a text widget\n","API_KEY = widgets.Password(\n"," value='',\n"," placeholder='',\n"," description='API_KEY:',\n"," disabled=False\n",")\n","\n","def md(t):\n"," display(Markdown(t))\n","\n","def bot_arch():\n"," mm(\"\"\"\n"," graph LR;\n"," user --> prompt\n"," prompt --> i_safety\n"," i_safety --> context\n"," context --> Llama_2\n"," Llama_2 --> output\n"," output --> o_safety\n"," i_safety --> memory\n"," o_safety --> memory\n"," memory --> context\n"," o_safety --> user\n"," classDef default fill:#CCE6FF,stroke:#84BCF5,textColor:#1C2B33,fontFamily:trebuchet ms;\n"," \"\"\")\n","\n","def fine_tuned_arch():\n"," mm(\"\"\"\n"," graph LR;\n"," Custom_Dataset --> Pre-trained_Llama\n"," Pre-trained_Llama --> Fine-tuned_Llama\n"," Fine-tuned_Llama --> RLHF\n"," RLHF --> |Loss:Cross-Entropy|Fine-tuned_Llama\n"," classDef default fill:#CCE6FF,stroke:#84BCF5,textColor:#1C2B33,fontFamily:trebuchet ms;\n"," \"\"\")\n","\n","def load_data_faiss_arch():\n"," mm(\"\"\"\n"," graph LR;\n"," documents --> textsplitter\n"," textsplitter --> embeddings\n"," embeddings --> vectorstore\n"," classDef default fill:#CCE6FF,stroke:#84BCF5,textColor:#1C2B33,fontFamily:trebuchet ms;\n"," \"\"\")\n","\n","def mem_context():\n"," mm(\"\"\"\n"," graph LR\n"," context(text)\n"," user_prompt --> context\n"," instruction --> context\n"," examples --> context\n"," memory --> context\n"," context --> tokenizer\n"," tokenizer --> embeddings\n"," embeddings --> LLM\n"," classDef default fill:#CCE6FF,stroke:#84BCF5,textColor:#1C2B33,fontFamily:trebuchet ms;\n"," \"\"\")\n"]},{"cell_type":"markdown","metadata":{"id":"i4Np_l_KtIno"},"source":["## **1 - Understanding Llama 2**"]},{"cell_type":"markdown","metadata":{"id":"PGPSI3M5PGTi"},"source":["### **1.1 - What is Llama 2?**\n","\n","* State of the art (SOTA), Open Source LLM\n","* 7B, 13B, 70B\n","* Pretrained + Chat\n","* Choosing model: Size, Quality, Cost, Speed\n","* [Research paper](https://ai.meta.com/research/publications/llama-2-open-foundation-and-fine-tuned-chat-models/)\n","\n","* [Responsible use guide](https://ai.meta.com/llama/responsible-use-guide/)"]},{"cell_type":"code","execution_count":7,"metadata":{"id":"OXRCC7wexZXd"},"outputs":[{"data":{"text/html":["<img src=\"https://mermaid.ink/img/CiAgZ3JhcGggTFI7CiAgICAgIGxsYW1hLTIgLS0+IGxsYW1hLTItN2IKICAgICAgbGxhbWEtMiAtLT4gbGxhbWEtMi0xM2IKICAgICAgbGxhbWEtMiAtLT4gbGxhbWEtMi03MGIKICAgICAgbGxhbWEtMi03YiAtLT4gbGxhbWEtMi03Yi1jaGF0CiAgICAgIGxsYW1hLTItMTNiIC0tPiBsbGFtYS0yLTEzYi1jaGF0CiAgICAgIGxsYW1hLTItNzBiIC0tPiBsbGFtYS0yLTcwYi1jaGF0CiAgICAgIGNsYXNzRGVmIGRlZmF1bHQgZmlsbDojQ0NFNkZGLHN0cm9rZTojODRCQ0Y1LHRleHRDb2xvcjojMUMyQjMzLGZvbnRGYW1pbHk6dHJlYnVjaGV0IG1zOwogIA==\"/>"],"text/plain":["<IPython.core.display.Image object>"]},"metadata":{},"output_type":"display_data"}],"source":["llama2_family()"]},{"cell_type":"markdown","metadata":{"id":"aYeHVVh45bdT"},"source":["### **1.2 - Accessing Llama 2**\n","* Download + Self Host (on-premise)\n","* Hosted API Platform (e.g. Replicate)\n","\n","* Hosted Container Platform (e.g. Azure, AWS, GCP)\n","\n"]},{"cell_type":"markdown","metadata":{"id":"kBuSay8vtzL4"},"source":["### **1.3 - Use Cases of Llama 2**\n","* Content Generation\n","* Chatbots\n","* Summarization\n","* Programming (e.g. Code Llama)\n","\n","* and many more..."]},{"cell_type":"markdown","metadata":{"id":"sd54g0OHuqBY"},"source":["## **2 - Using Llama 2**"]},{"cell_type":"markdown","metadata":{"id":"h3YGMDJidHtH"},"source":["### **2.1 - Install dependencies**"]},{"cell_type":"code","execution_count":8,"metadata":{"id":"VhN6hXwx7FCp"},"outputs":[{"name":"stdout","output_type":"stream","text":["Note: you may need to restart the kernel to use updated packages.\n"]}],"source":["# Install dependencies and initialize\n","%pip install -qU \\\n"," replicate \\\n"," langchain \\\n"," sentence_transformers \\\n"," pdf2image \\\n"," pdfminer \\\n"," pdfminer.six \\\n"," unstructured \\\n"," faiss-gpu"]},{"cell_type":"markdown","metadata":{},"source":["Here, first we are going to show how to use llama2 through Replicate hosted api"]},{"cell_type":"code","execution_count":9,"metadata":{"id":"Z8Y8qjEjmg50"},"outputs":[],"source":["# model we will use throughout the notebook\n","llama2_13b = \"meta/llama-2-13b-chat:f4e2de70d66816a838a89eeeb621910adffb0dd0baba3976c96980970978018d\""]},{"cell_type":"code","execution_count":14,"metadata":{"id":"8hkWpqWD28ho"},"outputs":[],"source":["# We will use Replicate hosted cloud environment\n","# Obtain Replicate API key → https://replicate.com/account/api-tokens)\n","# Find the model to use → we will use [`llama-2-13b-chat`](https://replicate.com/lucataco/llama-2-13b-chat)\n","\n","# enter your replicate api token\n","from getpass import getpass\n","import os\n","\n","REPLICATE_API_TOKEN = getpass()\n","os.environ[\"REPLICATE_API_TOKEN\"] = REPLICATE_API_TOKEN\n","\n","# alternatively, you can also store the tokens in environment variables and load it here"]},{"cell_type":"code","execution_count":15,"metadata":{"id":"bVCHZmETk36v"},"outputs":[],"source":["# we will use replicate's hosted api\n","import replicate\n","\n","# text completion with input prompt\n","def Completion(prompt):\n"," output = replicate.run(\n"," llama2_13b,\n"," input={\"prompt\": prompt, \"max_new_tokens\":1000}\n"," )\n"," return \"\".join(output)\n","\n","# chat completion with input prompt and system prompt\n","def ChatCompletion(prompt, system_prompt=None):\n"," output = replicate.run(\n"," llama2_13b,\n"," input={\"system_prompt\": system_prompt,\n"," \"prompt\": prompt,\n"," \"max_new_tokens\":1000}\n"," )\n"," return \"\".join(output)"]},{"cell_type":"markdown","metadata":{"id":"5Jxq0pmf6L73"},"source":["### **2.2 - Basic completion**"]},{"cell_type":"code","execution_count":16,"metadata":{"id":"H93zZBIk6tNU"},"outputs":[{"data":{"text/markdown":[" Why, thank you for asking! The typical color of a llama is... (drumroll please)... GRAY! Yes, llamas are known for their beautiful gray coats, which can range in shade from light to dark. Some llamas may also have white markings on their faces or legs, but overall, gray is the most common color you'll see among these lovely creatures. Ho ho ho, I hope that helps!"],"text/plain":["<IPython.core.display.Markdown object>"]},"metadata":{},"output_type":"display_data"}],"source":["output = Completion(prompt=\"The typical color of a llama is: \")\n","md(output)"]},{"cell_type":"markdown","metadata":{"id":"StccjUDh6W0Q"},"source":["### **2.3 - System prompts**\n"]},{"cell_type":"code","execution_count":17,"metadata":{"id":"VRnFogxd6rTc"},"outputs":[{"data":{"text/markdown":[" Gray."],"text/plain":["<IPython.core.display.Markdown object>"]},"metadata":{},"output_type":"display_data"}],"source":["output = ChatCompletion(\n"," prompt=\"The typical color of a llama is: \",\n"," system_prompt=\"respond with only one word\"\n"," )\n","md(output)"]},{"cell_type":"markdown","metadata":{"id":"Hp4GNa066pYy"},"source":["### **2.4 - Response formats**\n","* Can support different formatted outputs e.g. text, JSON, etc."]},{"cell_type":"code","execution_count":18,"metadata":{"id":"HTN79h4RptgQ"},"outputs":[{"data":{"text/markdown":[" {\n","\"answer\": \"The typical color of a llama is brown.\"\n","}"],"text/plain":["<IPython.core.display.Markdown object>"]},"metadata":{},"output_type":"display_data"}],"source":["output = ChatCompletion(\n"," prompt=\"The typical color of a llama is: \",\n"," system_prompt=\"response in json format\"\n"," )\n","md(output)"]},{"cell_type":"markdown","metadata":{"id":"cWs_s9y-avIT"},"source":["## **3 - Gen AI Application Architecture**\n"]},{"cell_type":"code","execution_count":19,"metadata":{"id":"j9BGuI-9AOL5"},"outputs":[{"data":{"text/html":["<img src=\"https://mermaid.ink/img/CiAgZmxvd2NoYXJ0IFRECiAgICBBW1VzZXJzXSAtLT4gQihBcHBsaWNhdGlvbnMgZS5nLiBtb2JpbGUsIHdlYikKICAgIEIgLS0+IHxIb3N0ZWQgQVBJfEMoUGxhdGZvcm1zIGUuZy4gQ3VzdG9tLCBIdWdnaW5nRmFjZSwgUmVwbGljYXRlKQogICAgQiAtLSBvcHRpb25hbCAtLT4gRShGcmFtZXdvcmtzIGUuZy4gTGFuZ0NoYWluKQogICAgQy0tPnxVc2VyIElucHV0fERbTGxhbWEgMl0KICAgIEQtLT58TW9kZWwgT3V0cHV0fEMKICAgIEUgLS0+IEMKICAgIGNsYXNzRGVmIGRlZmF1bHQgZmlsbDojQ0NFNkZGLHN0cm9rZTojODRCQ0Y1LHRleHRDb2xvcjojMUMyQjMzLGZvbnRGYW1pbHk6dHJlYnVjaGV0IG1zOwogIA==\"/>"],"text/plain":["<IPython.core.display.Image object>"]},"metadata":{},"output_type":"display_data"}],"source":["genai_app_arch()"]},{"cell_type":"markdown","metadata":{"id":"6UlxBtbgys6j"},"source":["## 4 - **Chatbot Architecture**\n","* User Prompts\n","* Input Safety\n","* Llama 2\n","* Output Safety\n","\n","* Memory & Context"]},{"cell_type":"code","execution_count":20,"metadata":{"id":"tO5HnB56ys6t"},"outputs":[{"data":{"text/html":["<img src=\"https://mermaid.ink/img/CiAgZ3JhcGggTFI7CiAgdXNlciAtLT4gcHJvbXB0CiAgcHJvbXB0IC0tPiBpX3NhZmV0eQogIGlfc2FmZXR5IC0tPiBjb250ZXh0CiAgY29udGV4dCAtLT4gTGxhbWFfMgogIExsYW1hXzIgLS0+IG91dHB1dAogIG91dHB1dCAtLT4gb19zYWZldHkKICBpX3NhZmV0eSAtLT4gbWVtb3J5CiAgb19zYWZldHkgLS0+IG1lbW9yeQogIG1lbW9yeSAtLT4gY29udGV4dAogIG9fc2FmZXR5IC0tPiB1c2VyCiAgY2xhc3NEZWYgZGVmYXVsdCBmaWxsOiNDQ0U2RkYsc3Ryb2tlOiM4NEJDRjUsdGV4dENvbG9yOiMxQzJCMzMsZm9udEZhbWlseTp0cmVidWNoZXQgbXM7CiAg\"/>"],"text/plain":["<IPython.core.display.Image object>"]},"metadata":{},"output_type":"display_data"}],"source":["bot_arch()"]},{"cell_type":"markdown","metadata":{"id":"r4DyTLD5ys6t"},"source":["### **4.1 - Chat conversation**\n","* LLMs are stateless\n","* Single Turn\n","\n","* Multi Turn (Memory)\n","\n"]},{"cell_type":"code","execution_count":21,"metadata":{"id":"EMM_egWMys6u"},"outputs":[{"data":{"text/markdown":[" Sure! The average lifespan of a llama is around 20-30 years."],"text/plain":["<IPython.core.display.Markdown object>"]},"metadata":{},"output_type":"display_data"}],"source":["# example of single turn chat\n","prompt_chat = \"What is the average lifespan of a Llama?\"\n","output = ChatCompletion(prompt=prompt_chat, system_prompt=\"answer the last question in few words\")\n","md(output)"]},{"cell_type":"code","execution_count":22,"metadata":{"id":"sZ7uVKDYucgi"},"outputs":[{"data":{"text/markdown":[" Sure! Here's my answer in a few words:\n","\n","Kangaroos."],"text/plain":["<IPython.core.display.Markdown object>"]},"metadata":{},"output_type":"display_data"}],"source":["# example without previous context. LLM's are stateless and cannot understand \"they\" without previous context\n","prompt_chat = \"What animal family are they?\"\n","output = ChatCompletion(prompt=prompt_chat, system_prompt=\"answer the last question in few words\")\n","md(output)"]},{"cell_type":"markdown","metadata":{"id":"WQl3wmfbyBQ1"},"source":["Chat app requires us to send in previous context to LLM to get in valid responses. Below is an example of Multi-turn chat."]},{"cell_type":"code","execution_count":23,"metadata":{"id":"t7SZe5fT3HG3"},"outputs":[{"data":{"text/markdown":[" Sure, I'd be happy to help! Llamas are members of the camelid family, which includes other animals like camels and alpacas."],"text/plain":["<IPython.core.display.Markdown object>"]},"metadata":{},"output_type":"display_data"}],"source":["# example of multi-turn chat, with storing previous context\n","prompt_chat = \"\"\"\n","User: What is the average lifespan of a Llama?\n","Assistant: Sure! The average lifespan of a llama is around 20-30 years.\n","User: What animal family are they?\n","\"\"\"\n","output = ChatCompletion(prompt=prompt_chat, system_prompt=\"answer the last question\")\n","md(output)"]},{"cell_type":"markdown","metadata":{"id":"moXnmJ_xyD10"},"source":["### **4.2 - Prompt Engineering**\n","Prompt engineering refers to the science of designing effective prompts to get desired responses.\n"]},{"cell_type":"markdown","metadata":{"id":"t-v-FeZ4ztTB"},"source":["#### **4.2.1 - In-Context Learning (e.g. Zero-shot, Few-shot)**\n"," * In-context learning - specific method of prompt engineering where demonstration of task are provided as part of prompt.\n"," 1. Zero-shot learning - model is performing tasks without any\n","input examples.\n"," 2. Few or “N-Shot” Learning - model is performing and behaving based on input examples in user's prompt.\n"]},{"cell_type":"code","execution_count":24,"metadata":{"id":"6W71MFNZyRkQ"},"outputs":[{"data":{"text/markdown":[" Cute"],"text/plain":["<IPython.core.display.Markdown object>"]},"metadata":{},"output_type":"display_data"}],"source":["# Zero-shot example. To get positive/negative/neutral sentiment, we need to give examples in the prompt\n","prompt = '''\n","Classify: I saw a Gecko.\n","Sentiment: ?\n","'''\n","output = ChatCompletion(prompt, system_prompt=\"one word response\")\n","md(output)"]},{"cell_type":"code","execution_count":25,"metadata":{"id":"MCQRjf1Y1RYJ"},"outputs":[{"data":{"text/markdown":[" Neutral"],"text/plain":["<IPython.core.display.Markdown object>"]},"metadata":{},"output_type":"display_data"}],"source":["# By giving examples to Llama, it understands the expected output format.\n","\n","prompt = '''\n","Classify: I love Llamas!\n","Sentiment: Positive\n","Classify: I dont like Snakes.\n","Sentiment: Negative\n","Classify: I saw a Gecko.\n","Sentiment:'''\n","\n","output = ChatCompletion(prompt, system_prompt=\"One word response\")\n","md(output)"]},{"cell_type":"code","execution_count":26,"metadata":{"id":"8UmdlTmpDZxA"},"outputs":[{"data":{"text/markdown":[" Luxurious."],"text/plain":["<IPython.core.display.Markdown object>"]},"metadata":{},"output_type":"display_data"}],"source":["# another zero-shot learning\n","prompt = '''\n","QUESTION: Vicuna?\n","ANSWER:'''\n","\n","output = ChatCompletion(prompt, system_prompt=\"one word response\")\n","md(output)"]},{"cell_type":"code","execution_count":27,"metadata":{"id":"M_EcsUo1zqFD"},"outputs":[{"data":{"text/markdown":[" Yes"],"text/plain":["<IPython.core.display.Markdown object>"]},"metadata":{},"output_type":"display_data"}],"source":["# Another few-shot learning example with formatted prompt.\n","\n","prompt = '''\n","QUESTION: Llama?\n","ANSWER: Yes\n","QUESTION: Alpaca?\n","ANSWER: Yes\n","QUESTION: Rabbit?\n","ANSWER: No\n","QUESTION: Vicuna?\n","ANSWER:'''\n","\n","output = ChatCompletion(prompt, system_prompt=\"one word response\")\n","md(output)"]},{"cell_type":"markdown","metadata":{"id":"mbr124Y197xl"},"source":["#### **4.2.2 - Chain of Thought**\n","* \"chain of thought\" or a coherent sequence of ideas is crucial for generating meaningful and contextually relevant responses\n","\n","* Hallucination on word problems"]},{"cell_type":"code","execution_count":28,"metadata":{"id":"Xn8zmLBQzpgj"},"outputs":[{"data":{"text/markdown":[" Sure! Here's the answer:\n","\n","Llama has 8 tennis balls now."],"text/plain":["<IPython.core.display.Markdown object>"]},"metadata":{},"output_type":"display_data"}],"source":["# Standard prompting\n","prompt = '''\n","Llama started with 5 tennis balls. It buys 2 more cans of tennis balls. Each can has 3 tennis balls. How many tennis balls does Llama have now?\n","'''\n","\n","output = ChatCompletion(prompt, system_prompt=\"provide short answer\")\n","md(output)"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"lKNOj79o1Kwu"},"outputs":[],"source":["# Chain-Of-Thought prompting\n","prompt = '''\n","Llama started with 5 tennis balls. It buys 2 more cans of tennis balls. Each can has 3 tennis balls. How many tennis balls does Llama have now?\n","Let's think step by step.\n","'''\n","\n","output = ChatCompletion(prompt, system_prompt=\"provide short answer\")\n","md(output)"]},{"cell_type":"markdown","metadata":{"id":"C7tDW-AH770Y"},"source":["### **4.3 - Retrieval Augmented Generation (RAG)**\n","* Prompt Eng Limitations (Knowledge cutoff & lack of specialized data)\n","\n","* Langchain\n","\n","Retrieval Augmented Generation(RAG) allows us to retrieve snippets of information from external data sources and augment it to the user's prompt to get tailored responses from Llama 2.\n","\n","\n"]},{"cell_type":"code","execution_count":29,"metadata":{"id":"Fl1LPltpRQD9"},"outputs":[{"data":{"text/html":["<img src=\"https://mermaid.ink/img/CiAgZmxvd2NoYXJ0IFRECiAgICBBW1VzZXIgUHJvbXB0c10gLS0+IEIoRnJhbWV3b3JrcyBlLmcuIExhbmdDaGFpbikKICAgIEIgPC0tPiB8RGF0YWJhc2UsIERvY3MsIFhMU3xDW2ZhOmZhLWRhdGFiYXNlIEV4dGVybmFsIERhdGFdCiAgICBCIC0tPnxBUEl8RFtMbGFtYSAyXQogICAgY2xhc3NEZWYgZGVmYXVsdCBmaWxsOiNDQ0U2RkYsc3Ryb2tlOiM4NEJDRjUsdGV4dENvbG9yOiMxQzJCMzMsZm9udEZhbWlseTp0cmVidWNoZXQgbXM7CiAg\"/>"],"text/plain":["<IPython.core.display.Image object>"]},"metadata":{},"output_type":"display_data"}],"source":["rag_arch()"]},{"cell_type":"markdown","metadata":{"id":"JJaGMLl_4vYm"},"source":["#### **4.3.1 - LangChain**\n","LangChain is a framework that helps make it easier to implement RAG.\n"]},{"cell_type":"code","execution_count":30,"metadata":{"id":"aoqU3KTcHTWN"},"outputs":[],"source":["# langchain setup\n","from langchain.llms import Replicate\n","# Use the Llama 2 model hosted on Replicate\n","# Temperature: Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value\n","# top_p: When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens\n","# max_new_tokens: Maximum number of tokens to generate. A word is generally 2-3 tokens\n","llama_model = Replicate(\n"," model=llama2_13b,\n"," model_kwargs={\"temperature\": 0.75,\"top_p\": 1, \"max_new_tokens\":1000}\n",")"]},{"cell_type":"code","execution_count":31,"metadata":{"id":"gAV2EkZqcruF"},"outputs":[{"name":"stderr","output_type":"stream","text":["[nltk_data] Downloading package punkt to\n","[nltk_data] /data/home/hamidnazeri/nltk_data...\n","[nltk_data] Unzipping tokenizers/punkt.zip.\n","[nltk_data] Downloading package averaged_perceptron_tagger to\n","[nltk_data] /data/home/hamidnazeri/nltk_data...\n","[nltk_data] Unzipping taggers/averaged_perceptron_tagger.zip.\n"]},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"008094e574614c2f8597bab6e7a2489d","version_major":2,"version_minor":0},"text/plain":["Downloading (…)a8e1d/.gitattributes: 0%| | 0.00/1.18k [00:00<?, ?B/s]"]},"metadata":{},"output_type":"display_data"},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"b6aa3b99dd7942169d8168856667775d","version_major":2,"version_minor":0},"text/plain":["Downloading (…)_Pooling/config.json: 0%| | 0.00/190 [00:00<?, ?B/s]"]},"metadata":{},"output_type":"display_data"},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"42b1ba514c9a4614a57c18e698389049","version_major":2,"version_minor":0},"text/plain":["Downloading (…)b20bca8e1d/README.md: 0%| | 0.00/10.6k [00:00<?, ?B/s]"]},"metadata":{},"output_type":"display_data"},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"50a9af560b204fcbb7a1c9b4eeb8e8ad","version_major":2,"version_minor":0},"text/plain":["Downloading (…)0bca8e1d/config.json: 0%| | 0.00/571 [00:00<?, ?B/s]"]},"metadata":{},"output_type":"display_data"},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"a979c95a88384e30979e5335eb47ebd4","version_major":2,"version_minor":0},"text/plain":["Downloading (…)ce_transformers.json: 0%| | 0.00/116 [00:00<?, ?B/s]"]},"metadata":{},"output_type":"display_data"},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"79e7104dd3eb46a2b1a2aa22467352f5","version_major":2,"version_minor":0},"text/plain":["Downloading (…)e1d/data_config.json: 0%| | 0.00/39.3k [00:00<?, ?B/s]"]},"metadata":{},"output_type":"display_data"},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"ddf9f9d4cc2d4b74be1ed12009e7f4fd","version_major":2,"version_minor":0},"text/plain":["Downloading pytorch_model.bin: 0%| | 0.00/438M [00:00<?, ?B/s]"]},"metadata":{},"output_type":"display_data"},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"2dc7dda15ab24dd6b42a95c86c8e4fc2","version_major":2,"version_minor":0},"text/plain":["Downloading (…)nce_bert_config.json: 0%| | 0.00/53.0 [00:00<?, ?B/s]"]},"metadata":{},"output_type":"display_data"},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"1736f5f5359d4840b95e5403dc8182a4","version_major":2,"version_minor":0},"text/plain":["Downloading (…)cial_tokens_map.json: 0%| | 0.00/239 [00:00<?, ?B/s]"]},"metadata":{},"output_type":"display_data"},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"fc6ddf842d184adb8348dcf7a5c3f3ec","version_major":2,"version_minor":0},"text/plain":["Downloading (…)a8e1d/tokenizer.json: 0%| | 0.00/466k [00:00<?, ?B/s]"]},"metadata":{},"output_type":"display_data"},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"58158aecc2d644408d96670533eb4be6","version_major":2,"version_minor":0},"text/plain":["Downloading (…)okenizer_config.json: 0%| | 0.00/363 [00:00<?, ?B/s]"]},"metadata":{},"output_type":"display_data"},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"b28ccdb382064937867f3b3f8f9265a0","version_major":2,"version_minor":0},"text/plain":["Downloading (…)8e1d/train_script.py: 0%| | 0.00/13.1k [00:00<?, ?B/s]"]},"metadata":{},"output_type":"display_data"},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"7c3ee2c088c8477fa9bfc4418fac118c","version_major":2,"version_minor":0},"text/plain":["Downloading (…)b20bca8e1d/vocab.txt: 0%| | 0.00/232k [00:00<?, ?B/s]"]},"metadata":{},"output_type":"display_data"},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"165879367cfb44ff97dacc38a72886c6","version_major":2,"version_minor":0},"text/plain":["Downloading (…)bca8e1d/modules.json: 0%| | 0.00/349 [00:00<?, ?B/s]"]},"metadata":{},"output_type":"display_data"},{"name":"stderr","output_type":"stream","text":["/data/home/hamidnazeri/miniconda/envs/llama-package/lib/python3.10/site-packages/torch/cuda/__init__.py:611: UserWarning: Can't initialize NVML\n"," warnings.warn(\"Can't initialize NVML\")\n"]}],"source":["# Step 1: load the external data source. In our case, we will load Meta’s “Responsible Use Guide” pdf document.\n","from langchain.document_loaders import OnlinePDFLoader\n","loader = OnlinePDFLoader(\"https://ai.meta.com/static-resource/responsible-use-guide/\")\n","documents = loader.load()\n","\n","# Step 2: Get text splits from document\n","from langchain.text_splitter import RecursiveCharacterTextSplitter\n","text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=20)\n","all_splits = text_splitter.split_documents(documents)\n","\n","# Step 3: Use the embedding model\n","from langchain.vectorstores import FAISS\n","from langchain.embeddings import HuggingFaceEmbeddings\n","model_name = \"sentence-transformers/all-mpnet-base-v2\" # embedding model\n","model_kwargs = {\"device\": \"cpu\"}\n","embeddings = HuggingFaceEmbeddings(model_name=model_name, model_kwargs=model_kwargs)\n","\n","# Step 4: Use vector store to store embeddings\n","vectorstore = FAISS.from_documents(all_splits, embeddings)"]},{"cell_type":"markdown","metadata":{"id":"K2l8S5tBxlkc"},"source":["#### **4.3.2 - LangChain Q&A Retriever**\n","* ConversationalRetrievalChain\n","\n","* Query the Source documents\n"]},{"cell_type":"code","execution_count":32,"metadata":{"id":"NmEhBe3Kiyre"},"outputs":[{"data":{"text/markdown":[" Sure! Here's my helpful answer based on the provided context:\n","\n","Meta is approaching open science by open sourcing code and datasets for machine translation, computer vision, and fairness evaluation, believing this will put these models in more people's hands and contribute to the infrastructure of the AI-developer community, ultimately benefiting all sizes of organizations globally. By doing so, Meta aims to democratize access and collaboration on risk management, empowering developers to drive breakthroughs and address global challenges responsibly."],"text/plain":["<IPython.core.display.Markdown object>"]},"metadata":{},"output_type":"display_data"}],"source":["# Query against your own data\n","from langchain.chains import ConversationalRetrievalChain\n","chain = ConversationalRetrievalChain.from_llm(llama_model, vectorstore.as_retriever(), return_source_documents=True)\n","\n","chat_history = []\n","query = \"How is Meta approaching open science in two short sentences?\"\n","result = chain({\"question\": query, \"chat_history\": chat_history})\n","md(result['answer'])"]},{"cell_type":"code","execution_count":33,"metadata":{"id":"CelLHIvoy2Ke"},"outputs":[{"data":{"text/markdown":[" Based on the provided context, here is my answer to your question:\n","\n","Meta's approach to open science has several benefits for the world, including:\n","\n","1. Democratization of access: By open sourcing code and datasets, Meta has made these resources more accessible to developers and researchers across the globe, regardless of their size or budget. This has led to a more level playing field for organizations of all sizes, allowing them to benefit from the advancements in AI technology.\n","2. Increased collaboration: Opening up research and development to the community has facilitated collaboration and knowledge sharing, leading to improved exploratory research and large-scale production deployment. This collective wisdom and diversity of perspectives have the potential to accelerate progress and improve the safety and robustness of AI models.\n","3. Improved governance and accountability: Meta's commitment to responsible AI principles such as fairness, inclusion, privacy, security, and transparency helps ensure that the power of AI is harnessed to address global challenges in a responsible manner. The implementation of safety measures and risk management mechanisms helps mitigate novel risks associated with generative AI tools.\n","4. Advancements in scientific discovery: Meta's open source releases of cutting-edge LLMs like Llama have enabled researchers to explore new use cases and applications, potentially revolutionizing sectors like education, agriculture, climate management, and cybersecurity. These advancements have the potential to unlock significant social and economic benefits.\n","5. Empowerment of developers: By providing resources for developers and enabling them to drive breakthroughs, Meta's approach empowers developers globally to create innovative products and solutions that can address pressing global challenges.\n","\n","As a result of this strategy, we can expect:\n","\n","1. Increased adoption of AI technology across industries and geographies, leading to improved efficiency, productivity, and decision-making.\n","2. Further advancements in scientific discovery and applications of AI technology, leading to potential breakthroughs and improvements in various fields.\n","3. Enhanced collaboration and knowledge sharing within the AI community, fostering a culture of responsibility and accountability in AI development and deployment.\n","4. Improved governance and regulation of AI technology, ensuring that the benefits of AI are realized while minimizing its risks and negative impacts."],"text/plain":["<IPython.core.display.Markdown object>"]},"metadata":{},"output_type":"display_data"}],"source":["# This time your previous question and answer will be included as a chat history which will enable the ability\n","# to ask follow up questions.\n","chat_history = [(query, result[\"answer\"])]\n","query = \"How is it benefiting the world?\"\n","result = chain({\"question\": query, \"chat_history\": chat_history})\n","md(result['answer'])"]},{"cell_type":"markdown","metadata":{"id":"TEvefAWIJONx"},"source":["## **5 - Fine-Tuning Models**\n","\n","* Limitatons of Prompt Eng and RAG\n","* Fine-Tuning Arch\n","* Types (PEFT, LoRA, QLoRA)\n","* Using PyTorch for Pre-Training & Fine-Tuning\n","\n","* Evals + Quality\n"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"0a9CvJ8YcTzV"},"outputs":[],"source":["fine_tuned_arch()"]},{"cell_type":"markdown","metadata":{"id":"_8lcgdZa8onC"},"source":["## **6 - Responsible AI**\n","\n","* Power + Responsibility\n","* Hallucinations\n","* Input & Output Safety\n","* Red-teaming (simulating real-world cyber attackers)\n","* [Responsible Use Guide](https://ai.meta.com/llama/responsible-use-guide/)\n","\n"]},{"cell_type":"markdown","metadata":{"id":"pbqb006R-T_k"},"source":["##**7 - Conclusion**\n","* Active research on LLMs and Llama\n","* Leverage the power of Llama and its open community\n","* Safety and responsible use is paramount!\n","\n","* Call-To-Action\n"," * [Replicate Free Credits](https://replicate.fyi/connect2023) for Connect attendees!\n"," * This notebook is available through Llama Github recipes\n"," * Use Llama in your projects and give us feedback\n"]},{"cell_type":"markdown","metadata":{"id":"gSz5dTMxp7xo"},"source":["#### **Resources**\n","- [GitHub - Llama 2](https://github.com/facebookresearch/llama)\n","- [Github - LLama 2 Recipes](https://github.com/facebookresearch/llama-recipes)\n","- [Llama 2](https://ai.meta.com/llama/)\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","- [Replicate](https://replicate.com/meta/)\n","- [LangChain](https://www.langchain.com/)\n","\n"]},{"cell_type":"markdown","metadata":{"id":"V7aI6fhZp-KC"},"source":["#### **Authors & Contact**\n"," * asangani@meta.com, [Amit Sangani | LinkedIn](https://www.linkedin.com/in/amitsangani/)\n"," * mohsena@meta.com, [Mohsen Agsen | LinkedIn](https://www.linkedin.com/in/mohsen-agsen-62a9791/)\n"]}],"metadata":{"colab":{"collapsed_sections":["ioVMNcTesSEk"],"machine_shape":"hm","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":"3.10.13"}},"nbformat":4,"nbformat_minor":0}
+{"cells":[{"cell_type":"markdown","source":[""],"metadata":{"id":"RJSnI0Xy-kCm"}},{"cell_type":"markdown","metadata":{"id":"LERqQn5v8-ak"},"source":["# **Getting to know Llama 2: Everything you need to start building**\n","Our goal in this session is to provide a guided tour of Llama 2, including understanding different Llama 2 models, how and where to access them, Generative AI and Chatbot architectures, prompt engineering, RAG (Retrieval Augmented Generation), Fine-tuning and more. All this is implemented with a starter code for you to take it and use it in your Llama 2 projects."]},{"cell_type":"markdown","source":["##**0 - Prerequisites**\n","* Basic understanding of Large Language Models\n","\n","* Basic understanding of Python"],"metadata":{"id":"ioVMNcTesSEk"}},{"cell_type":"code","execution_count":null,"metadata":{"id":"ktEA7qXmwdUM"},"outputs":[],"source":["# presentation layer code\n","\n","import base64\n","from IPython.display import Image, display\n","import matplotlib.pyplot as plt\n","\n","def mm(graph):\n"," graphbytes = graph.encode(\"ascii\")\n"," base64_bytes = base64.b64encode(graphbytes)\n"," base64_string = base64_bytes.decode(\"ascii\")\n"," display(Image(url=\"https://mermaid.ink/img/\" + base64_string))\n","\n","def genai_app_arch():\n"," mm(\"\"\"\n"," flowchart TD\n"," A[Users] --> B(Applications e.g. mobile, web)\n"," B --> |Hosted API|C(Platforms e.g. Custom, HuggingFace, Replicate)\n"," B -- optional --> E(Frameworks e.g. LangChain)\n"," C-->|User Input|D[Llama 2]\n"," D-->|Model Output|C\n"," E --> C\n"," classDef default fill:#CCE6FF,stroke:#84BCF5,textColor:#1C2B33,fontFamily:trebuchet ms;\n"," \"\"\")\n","\n","def rag_arch():\n"," mm(\"\"\"\n"," flowchart TD\n"," A[User Prompts] --> B(Frameworks e.g. LangChain)\n"," B <--> |Database, Docs, XLS|C[fa:fa-database External Data]\n"," B -->|API|D[Llama 2]\n"," classDef default fill:#CCE6FF,stroke:#84BCF5,textColor:#1C2B33,fontFamily:trebuchet ms;\n"," \"\"\")\n","\n","def llama2_family():\n"," mm(\"\"\"\n"," graph LR;\n"," llama-2 --> llama-2-7b\n"," llama-2 --> llama-2-13b\n"," llama-2 --> llama-2-70b\n"," llama-2-7b --> llama-2-7b-chat\n"," llama-2-13b --> llama-2-13b-chat\n"," llama-2-70b --> llama-2-70b-chat\n"," classDef default fill:#CCE6FF,stroke:#84BCF5,textColor:#1C2B33,fontFamily:trebuchet ms;\n"," \"\"\")\n","\n","def apps_and_llms():\n"," mm(\"\"\"\n"," graph LR;\n"," users --> apps\n"," apps --> frameworks\n"," frameworks --> platforms\n"," platforms --> Llama 2\n"," classDef default fill:#CCE6FF,stroke:#84BCF5,textColor:#1C2B33,fontFamily:trebuchet ms;\n"," \"\"\")\n","\n","import ipywidgets as widgets\n","from IPython.display import display, Markdown\n","\n","# Create a text widget\n","API_KEY = widgets.Password(\n"," value='',\n"," placeholder='',\n"," description='API_KEY:',\n"," disabled=False\n",")\n","\n","def md(t):\n"," display(Markdown(t))\n","\n","def bot_arch():\n"," mm(\"\"\"\n"," graph LR;\n"," user --> prompt\n"," prompt --> i_safety\n"," i_safety --> context\n"," context --> Llama_2\n"," Llama_2 --> output\n"," output --> o_safety\n"," i_safety --> memory\n"," o_safety --> memory\n"," memory --> context\n"," o_safety --> user\n"," classDef default fill:#CCE6FF,stroke:#84BCF5,textColor:#1C2B33,fontFamily:trebuchet ms;\n"," \"\"\")\n","\n","def fine_tuned_arch():\n"," mm(\"\"\"\n"," graph LR;\n"," Custom_Dataset --> Pre-trained_Llama\n"," Pre-trained_Llama --> Fine-tuned_Llama\n"," Fine-tuned_Llama --> RLHF\n"," RLHF --> |Loss:Cross-Entropy|Fine-tuned_Llama\n"," classDef default fill:#CCE6FF,stroke:#84BCF5,textColor:#1C2B33,fontFamily:trebuchet ms;\n"," \"\"\")\n","\n","def load_data_faiss_arch():\n"," mm(\"\"\"\n"," graph LR;\n"," documents --> textsplitter\n"," textsplitter --> embeddings\n"," embeddings --> vectorstore\n"," classDef default fill:#CCE6FF,stroke:#84BCF5,textColor:#1C2B33,fontFamily:trebuchet ms;\n"," \"\"\")\n","\n","def mem_context():\n"," mm(\"\"\"\n"," graph LR\n"," context(text)\n"," user_prompt --> context\n"," instruction --> context\n"," examples --> context\n"," memory --> context\n"," context --> tokenizer\n"," tokenizer --> embeddings\n"," embeddings --> LLM\n"," classDef default fill:#CCE6FF,stroke:#84BCF5,textColor:#1C2B33,fontFamily:trebuchet ms;\n"," \"\"\")\n"]},{"cell_type":"markdown","source":["##**1 - Understanding Llama 2**"],"metadata":{"id":"i4Np_l_KtIno"}},{"cell_type":"markdown","metadata":{"id":"PGPSI3M5PGTi"},"source":["### **1.1 - What is Llama 2?**\n","\n","* State of the art (SOTA), Open Source LLM\n","* 7B, 13B, 70B\n","* Pretrained + Chat\n","* Choosing model: Size, Quality, Cost, Speed\n","* [Research paper](https://ai.meta.com/research/publications/llama-2-open-foundation-and-fine-tuned-chat-models/)\n","\n","* [Responsible use guide](https://ai.meta.com/llama/responsible-use-guide/)"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"OXRCC7wexZXd"},"outputs":[],"source":["llama2_family()"]},{"cell_type":"markdown","metadata":{"id":"aYeHVVh45bdT"},"source":["###**1.2 - Accessing Llama 2**\n","* Download + Self Host (on-premise)\n","* Hosted API Platform (e.g. [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","source":["### **1.3 - Use Cases of Llama 2**\n","* Content Generation\n","* Chatbots\n","* Summarization\n","* Programming (e.g. Code Llama)\n","\n","* and many more..."],"metadata":{"id":"kBuSay8vtzL4"}},{"cell_type":"markdown","source":["##**2 - Using Llama 2**\n","\n","In this notebook, we are going to access [Llama 13b chat model](https://replicate.com/meta/llama-2-13b-chat) using hosted API from Replicate."],"metadata":{"id":"sd54g0OHuqBY"}},{"cell_type":"markdown","metadata":{"id":"h3YGMDJidHtH"},"source":["### **2.1 - Install dependencies**"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"VhN6hXwx7FCp"},"outputs":[],"source":["# Install dependencies and initialize\n","%pip install -qU \\\n"," replicate \\\n"," langchain \\\n"," sentence_transformers \\\n"," pdf2image \\\n"," pdfminer \\\n"," pdfminer.six \\\n"," unstructured \\\n"," faiss-gpu"]},{"cell_type":"code","source":["# model url on Replicate platform that we will use for inferencing\n","# We will use llama 23b chat model hosted on replicate server ()\n","\n","llama2_13b = \"meta/llama-2-13b-chat:f4e2de70d66816a838a89eeeb621910adffb0dd0baba3976c96980970978018d\""],"metadata":{"id":"Z8Y8qjEjmg50"},"execution_count":null,"outputs":[]},{"cell_type":"code","execution_count":null,"metadata":{"id":"8hkWpqWD28ho"},"outputs":[],"source":["# We will use Replicate hosted cloud environment\n","# Obtain Replicate API key → https://replicate.com/account/api-tokens)\n","\n","# enter your replicate api token\n","from getpass import getpass\n","import os\n","\n","REPLICATE_API_TOKEN = getpass()\n","os.environ[\"REPLICATE_API_TOKEN\"] = REPLICATE_API_TOKEN\n","\n","# alternatively, you can also store the tokens in environment variables and load it here"]},{"cell_type":"code","source":["# we will use replicate's hosted api\n","import replicate\n","\n","# text completion with input prompt\n","def Completion(prompt):\n"," output = replicate.run(\n"," llama2_13b,\n"," input={\"prompt\": prompt, \"max_new_tokens\":1000}\n"," )\n"," return \"\".join(output)\n","\n","# chat completion with input prompt and system prompt\n","def ChatCompletion(prompt, system_prompt=None):\n"," output = replicate.run(\n"," llama2_13b,\n"," input={\"system_prompt\": system_prompt,\n"," \"prompt\": prompt,\n"," \"max_new_tokens\":1000}\n"," )\n"," return \"\".join(output)"],"metadata":{"id":"bVCHZmETk36v"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"5Jxq0pmf6L73"},"source":["### **2.2 - Basic completion**"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"H93zZBIk6tNU"},"outputs":[],"source":["output = Completion(prompt=\"The typical color of a llama is: \")\n","md(output)"]},{"cell_type":"markdown","metadata":{"id":"StccjUDh6W0Q"},"source":["### **2.3 - System prompts**\n"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"VRnFogxd6rTc"},"outputs":[],"source":["output = ChatCompletion(\n"," prompt=\"The typical color of a llama is: \",\n"," system_prompt=\"respond with only one word\"\n"," )\n","md(output)"]},{"cell_type":"markdown","metadata":{"id":"Hp4GNa066pYy"},"source":["### **2.4 - Response formats**\n","* Can support different formatted outputs e.g. text, JSON, etc."]},{"cell_type":"code","source":["output = ChatCompletion(\n"," prompt=\"The typical color of a llama is: \",\n"," system_prompt=\"response in json format\"\n"," )\n","md(output)"],"metadata":{"id":"HTN79h4RptgQ"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"cWs_s9y-avIT"},"source":["## **3 - Gen AI Application Architecture**\n","\n","Here is the high-level tech stack/architecture of Generative AI application."]},{"cell_type":"code","source":["genai_app_arch()"],"metadata":{"id":"j9BGuI-9AOL5"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"6UlxBtbgys6j"},"source":["##4 - **Chatbot Architecture**\n","\n","Here are the key components and the information flow in a chatbot.\n","\n","* User Prompts\n","* Input Safety\n","* Llama 2\n","* Output Safety\n","\n","* Memory & Context"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"tO5HnB56ys6t"},"outputs":[],"source":["bot_arch()"]},{"cell_type":"markdown","metadata":{"id":"r4DyTLD5ys6t"},"source":["### **4.1 - Chat conversation**\n","* LLMs are stateless\n","* Single Turn\n","\n","* Multi Turn (Memory)\n","\n"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"EMM_egWMys6u"},"outputs":[],"source":["# example of single turn chat\n","prompt_chat = \"What is the average lifespan of a Llama?\"\n","output = ChatCompletion(prompt=prompt_chat, system_prompt=\"answer the last question in few words\")\n","md(output)"]},{"cell_type":"code","source":["# example without previous context. LLM's are stateless and cannot understand \"they\" without previous context\n","prompt_chat = \"What animal family are they?\"\n","output = ChatCompletion(prompt=prompt_chat, system_prompt=\"answer the last question in few words\")\n","md(output)"],"metadata":{"id":"sZ7uVKDYucgi"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":["Chat app requires us to send in previous context to LLM to get in valid responses. Below is an example of Multi-turn chat."],"metadata":{"id":"WQl3wmfbyBQ1"}},{"cell_type":"code","source":["# example of multi-turn chat, with storing previous context\n","prompt_chat = \"\"\"\n","User: What is the average lifespan of a Llama?\n","Assistant: Sure! The average lifespan of a llama is around 20-30 years.\n","User: What animal family are they?\n","\"\"\"\n","output = ChatCompletion(prompt=prompt_chat, system_prompt=\"answer the last question\")\n","md(output)"],"metadata":{"id":"t7SZe5fT3HG3"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"moXnmJ_xyD10"},"source":["### **4.2 - Prompt Engineering**\n","* Prompt engineering refers to the science of designing effective prompts to get desired responses\n","\n","* Helps reduce hallucination\n"]},{"cell_type":"markdown","metadata":{"id":"t-v-FeZ4ztTB"},"source":["#### **4.2.1 - In-Context Learning (e.g. Zero-shot, Few-shot)**\n"," * In-context learning - specific method of prompt engineering where demonstration of task are provided as part of prompt.\n"," 1. Zero-shot learning - model is performing tasks without any\n","input examples.\n"," 2. Few or “N-Shot” Learning - model is performing and behaving based on input examples in user's prompt."]},{"cell_type":"code","execution_count":null,"metadata":{"id":"6W71MFNZyRkQ"},"outputs":[],"source":["# Zero-shot example. To get positive/negative/neutral sentiment, we need to give examples in the prompt\n","prompt = '''\n","Classify: I saw a Gecko.\n","Sentiment: ?\n","'''\n","output = ChatCompletion(prompt, system_prompt=\"one word response\")\n","md(output)"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"MCQRjf1Y1RYJ"},"outputs":[],"source":["# By giving examples to Llama, it understands the expected output format.\n","\n","prompt = '''\n","Classify: I love Llamas!\n","Sentiment: Positive\n","Classify: I dont like Snakes.\n","Sentiment: Negative\n","Classify: I saw a Gecko.\n","Sentiment:'''\n","\n","output = ChatCompletion(prompt, system_prompt=\"One word response\")\n","md(output)"]},{"cell_type":"code","source":["# another zero-shot learning\n","prompt = '''\n","QUESTION: Vicuna?\n","ANSWER:'''\n","\n","output = ChatCompletion(prompt, system_prompt=\"one word response\")\n","md(output)"],"metadata":{"id":"8UmdlTmpDZxA"},"execution_count":null,"outputs":[]},{"cell_type":"code","execution_count":null,"metadata":{"id":"M_EcsUo1zqFD"},"outputs":[],"source":["# Another few-shot learning example with formatted prompt.\n","\n","prompt = '''\n","QUESTION: Llama?\n","ANSWER: Yes\n","QUESTION: Alpaca?\n","ANSWER: Yes\n","QUESTION: Rabbit?\n","ANSWER: No\n","QUESTION: Vicuna?\n","ANSWER:'''\n","\n","output = ChatCompletion(prompt, system_prompt=\"one word response\")\n","md(output)"]},{"cell_type":"markdown","metadata":{"id":"mbr124Y197xl"},"source":["#### **4.2.2 - Chain of Thought**\n","\"Chain of thought\" enables complex reasoning through logical step by step thinking and generates meaningful and contextually relevant responses."]},{"cell_type":"code","source":["# Standard prompting\n","prompt = '''\n","Llama started with 5 tennis balls. It buys 2 more cans of tennis balls. Each can has 3 tennis balls. How many tennis balls does Llama have now?\n","'''\n","\n","output = ChatCompletion(prompt, system_prompt=\"provide short answer\")\n","md(output)"],"metadata":{"id":"Xn8zmLBQzpgj"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["# Chain-Of-Thought prompting\n","prompt = '''\n","Llama started with 5 tennis balls. It buys 2 more cans of tennis balls. Each can has 3 tennis balls. How many tennis balls does Llama have now?\n","Let's think step by step.\n","'''\n","\n","output = ChatCompletion(prompt, system_prompt=\"provide short answer\")\n","md(output)"],"metadata":{"id":"lKNOj79o1Kwu"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"C7tDW-AH770Y"},"source":["### **4.3 - Retrieval Augmented Generation (RAG)**\n","* Prompt Eng Limitations - Knowledge cutoff & lack of specialized data\n","\n","* Retrieval Augmented Generation(RAG) allows us to retrieve snippets of information from external data sources and augment it to the user's prompt to get tailored responses from Llama 2.\n","\n","For our demo, we are going to download an external PDF file from a URL and query against the content in the pdf file to get contextually relevant information back with the help of Llama!\n","\n","\n","\n"]},{"cell_type":"code","source":["rag_arch()"],"metadata":{"id":"Fl1LPltpRQD9"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":["#### **4.3.1 - LangChain**\n","LangChain is a framework that helps make it easier to implement RAG."],"metadata":{"id":"JJaGMLl_4vYm"}},{"cell_type":"code","execution_count":null,"metadata":{"id":"aoqU3KTcHTWN"},"outputs":[],"source":["# langchain setup\n","from langchain.llms import Replicate\n","# Use the Llama 2 model hosted on Replicate\n","# Temperature: Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value\n","# top_p: When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens\n","# max_new_tokens: Maximum number of tokens to generate. A word is generally 2-3 tokens\n","llama_model = Replicate(\n"," model=llama2_13b,\n"," model_kwargs={\"temperature\": 0.75,\"top_p\": 1, \"max_new_tokens\":1000}\n",")"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"gAV2EkZqcruF"},"outputs":[],"source":["# Step 1: load the external data source. In our case, we will load Meta’s “Responsible Use Guide” pdf document.\n","from langchain.document_loaders import OnlinePDFLoader\n","loader = OnlinePDFLoader(\"https://ai.meta.com/static-resource/responsible-use-guide/\")\n","documents = loader.load()\n","\n","# Step 2: Get text splits from document\n","from langchain.text_splitter import RecursiveCharacterTextSplitter\n","text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=20)\n","all_splits = text_splitter.split_documents(documents)\n","\n","# Step 3: Use the embedding model\n","from langchain.vectorstores import FAISS\n","from langchain.embeddings import HuggingFaceEmbeddings\n","model_name = \"sentence-transformers/all-mpnet-base-v2\" # embedding model\n","model_kwargs = {\"device\": \"cpu\"}\n","embeddings = HuggingFaceEmbeddings(model_name=model_name, model_kwargs=model_kwargs)\n","\n","# Step 4: Use vector store to store embeddings\n","vectorstore = FAISS.from_documents(all_splits, embeddings)"]},{"cell_type":"markdown","metadata":{"id":"K2l8S5tBxlkc"},"source":["#### **4.3.2 - LangChain Q&A Retriever**\n","* ConversationalRetrievalChain\n","\n","* Query the Source documents\n"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"NmEhBe3Kiyre"},"outputs":[],"source":["# Query against your own data\n","from langchain.chains import ConversationalRetrievalChain\n","chain = ConversationalRetrievalChain.from_llm(llama_model, vectorstore.as_retriever(), return_source_documents=True)\n","\n","chat_history = []\n","query = \"How is Meta approaching open science in two short sentences?\"\n","result = chain({\"question\": query, \"chat_history\": chat_history})\n","md(result['answer'])"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"CelLHIvoy2Ke"},"outputs":[],"source":["# This time your previous question and answer will be included as a chat history which will enable the ability\n","# to ask follow up questions.\n","chat_history = [(query, result[\"answer\"])]\n","query = \"How is it benefiting the world?\"\n","result = chain({\"question\": query, \"chat_history\": chat_history})\n","md(result['answer'])"]},{"cell_type":"markdown","source":["## **5 - Fine-Tuning Models**\n","\n","* Limitatons of Prompt Eng and RAG\n","* Fine-Tuning Arch\n","* Types (PEFT, LoRA, QLoRA)\n","* Using PyTorch for Pre-Training & Fine-Tuning\n","\n","* Evals + Quality\n"],"metadata":{"id":"TEvefAWIJONx"}},{"cell_type":"code","source":["fine_tuned_arch()"],"metadata":{"id":"0a9CvJ8YcTzV"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"_8lcgdZa8onC"},"source":["## **6 - Responsible AI**\n","\n","* Power + Responsibility\n","* Hallucinations\n","* Input & Output Safety\n","* Red-teaming (simulating real-world cyber attackers)\n","* [Responsible Use Guide](https://ai.meta.com/llama/responsible-use-guide/)\n","\n"]},{"cell_type":"markdown","metadata":{"id":"pbqb006R-T_k"},"source":["##**7 - Conclusion**\n","* Active research on LLMs and Llama\n","* Leverage the power of Llama and its open community\n","* Safety and responsible use is paramount!\n","\n","* Call-To-Action\n"," * [Replicate Free Credits](https://replicate.fyi/connect2023) for Connect attendees!\n"," * This notebook is available through Llama Github recipes\n"," * Use Llama in your projects and give us feedback\n"]},{"cell_type":"markdown","source":["#### **Resources**\n","- [GitHub - Llama 2](https://github.com/facebookresearch/llama)\n","- [Github - LLama 2 Recipes](https://github.com/facebookresearch/llama-recipes)\n","- [Llama 2](https://ai.meta.com/llama/)\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","- [Replicate](https://replicate.com/meta/)\n","- [LangChain](https://www.langchain.com/)\n","\n"],"metadata":{"id":"gSz5dTMxp7xo"}},{"cell_type":"markdown","source":["#### **Authors & Contact**\n"," * asangani@meta.com, [Amit Sangani | LinkedIn](https://www.linkedin.com/in/amitsangani/)\n"," * mohsena@meta.com, [Mohsen Agsen | LinkedIn](https://www.linkedin.com/in/mohsen-agsen-62a9791/)\n"],"metadata":{"id":"V7aI6fhZp-KC"}}],"metadata":{"colab":{"provenance":[],"machine_shape":"hm","collapsed_sections":["ioVMNcTesSEk"],"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":"3.9.6"}},"nbformat":4,"nbformat_minor":0}
\ No newline at end of file