Computing Notes

Kotlin Multiplatform

Kotlin, Kotlin Multiplatform, Mobile App Development

https://kotlinlang.org/docs/multiplatform-get-started.html https://www.jetbrains.com/help/kotlin-multiplatform-dev/multiplatform-create-first-app.html Set up Environment: https://www.jetbrains.com/help/kotlin-multiplatform-dev/multiplatform-setup.html?_gl=1%2A1rp5et3%2A_ga%2AMTIxMDY0OTczOC4xNzI4MzIzNTE0%2A_ga_9J976DJZ68%2AMTcyODMyMzUxNC4xLjAuMTcyODMyMzY2My41MS4wLjA.%2A_gcl_au%2AMTcwNTk2OTcyMy4xNzI4MzIzNTIz Check Environment: Install brew if necessary, brew.sh There could be various issues: Solutions: 1. Java Not Found Problem: The Java Development Kit (JDK) is missing. Solution: Install the JDK by downloading it from the official Oracle website or via Homebrew: For macOS, you can also use Homebrew: brew install ... Read More

Installing HomeBrew

Tools

Go to terminal and run this:/bin/bash -c “$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)” https://brew.sh

How to download LLAMA models?

Large Language Models

2. You may need access in both HuggingFace and Meta Website. 3. Once approved you receive email from both (normall its quick within minutes) 4. Specially with email from meta, you get the link to download. 5. Then just follow, these steps– https://github.com/meta-llama/llama-models/blob/main/README.md Links: In Google colab: !cp -r /root/.llama/checkpoints/Llama-2-7b /content/drive/MyDrive/

LoRA

Large Language Models

What is Lora? How Fine-Tuning works?

Github README.md file.

Git, GitHub

Main Source:https://docs.github.com/en/get-started/writing-on-github/getting-started-with-writing-and-formatting-on-github/basic-writing-and-formatting-syntax References:

Streamlit, Gradio, Docker

Tools

Streamlit: Gradio Docker

Example code: Fine-tunning LLM using LoRA

Large Language Models, Machine Learning

Best resources:

Building Large Language Models (LLMs)

Large Language Models, Machine Learning

Pre-Training. Post-Training. Language Modeling. P(the, mouse, ate, the, cheese) = 0.02 – syntactic knowledgeP(the, the, mouse, ate,cheese) = 0.0001 – semantic knowledgeP(…) Auto-Reggressive (AR) language model: Predict next word. Steps: she likely prefers: tokenize -> 1 -she, 2-likely, 3-prefers => pass to blackbox model => get probability distribution over next word prediction – sample & ... Read More

Fine Tuning LLMs

Large Language Models, Machine Learning

Requirements: Challenges: Parameter Tuning: References:

What is Transformer?

Large Language Models, Machine Learning

Used by: Primary Innovations: Key Terms: Visual Explaination: Example:https://aws.amazon.com/what-is/transformers-in-artificial-intelligence/ References: