https://github.com/sudarshan-koirala/llm-resources
Repo that contains resources to learn or get started with Large Language Models (LLMs)
https://github.com/sudarshan-koirala/llm-resources
Last synced: 3 months ago
JSON representation
Repo that contains resources to learn or get started with Large Language Models (LLMs)
- Host: GitHub
- URL: https://github.com/sudarshan-koirala/llm-resources
- Owner: sudarshan-koirala
- License: mit
- Created: 2024-01-14T11:45:57.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2025-08-01T12:29:28.000Z (4 months ago)
- Last Synced: 2025-08-01T14:42:33.713Z (4 months ago)
- Size: 45.9 KB
- Stars: 63
- Watchers: 3
- Forks: 22
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- jimsghstars - sudarshan-koirala/llm-resources - Repo that contains resources to learn or get started with Large Language Models (LLMs) (Others)
README
Hello 👋, this is live-in document, might be updated as you are reading this 😎🧠
Update June 2025: Decided to create a file for each month to organize the resources.
# Resources to get started with Large Language Models (LLMs)
### [My Youtube Channel](https://www.youtube.com/@datasciencebasics)
- To be clear, this is not a roadmap for `getting started` with LLMs.
- I am not covering the books you should study, university studies, certificates, etc.
- I assume you have basic understanding of NLP stuffs, programming knowledge ( mainly Python and Maths ).
- You might argue, why Maths as everything is automated. Well, well, behind the scene, almost everything is Maths 🧠 )
- Calculus, Probability, Linear Algebra
- You need to know, Lets say what is matrix, how dot product works, etc etc.
- These are some of the resources which I suggest you to get started.
- After knowing the basics and how things work, it's upon you, what to do ( Or lets say if it's your cup of tea / coffee or not )
> Remember one thing, using LLMs and implementing are two different things, you need not necessary know how to implement, but you need to know how to use it in right way.
## Videos in Neural Networks and LLMs
- [A Hacker's Guide to Language Models](https://youtu.be/jkrNMKz9pWU?si=-PLRJrXB80E27Q_m) by Jeremy Howard.
- [[1hr Talk] Intro to Large Language Models](https://youtu.be/zjkBMFhNj_g?si=hw-BLphS85ORXL7i) by Andrej Karpathy.
- [Neural Networks: Zero to Hero](https://youtube.com/playlist?list=PLAqhIrjkxbuWI23v9cThsA9GvCAUhRvKZ&si=eTu3ESyFvq7JFdPD) by Andrej Karpathy.
- [Building RAG from scratch Using Python, LangChain and OpenAI API](https://youtu.be/BrsocJb-fAo?si=13-fYpjIBp9rmdhw) by Santiago.
---
## Free Courses
- [fast.ai courses](https://www.fast.ai/) --> `Optional but highly recommended`
- [DeepLearning.AI short courses](https://www.deeplearning.ai/short-courses/) -- My request, try to complete all this free short courses.
- [DeepLearning.AI Specializations](https://www.deeplearning.ai/courses/)
---
## Prompt Engineering
- [Prompt Engineering Guide](https://www.promptingguide.ai/)
- [OpenAI doc about Prompt Engineering](https://platform.openai.com/docs/guides/prompt-engineering)
- [Strategies to harness the power of LLMs](https://towardsdatascience.com/how-i-won-singapores-gpt-4-prompt-engineering-competition-34c195a93d41)
-[Prompt Engineering](https://github.com/NirDiamant/Prompt_Engineering)
- There is one from deeplearing.ai free short courses too about ChatGPT Prompt Engineering for Developers.
- There are many courses, articles, videos about this topic, it needs constant learning and experimenting.
---
## Frameworks which I have explored untill now, there are many, you can give a try ( your world, your rules )
- [LangChain](https://www.langchain.com/)
- [All you need to know about LangChain](https://youtu.be/EIejozA1W7I?si=rPBJnh7uEWVRa8ce)
- [LlamaIndex](https://www.llamaindex.ai/)
- [All you need to know about LlamaIndex](https://youtu.be/FbQowFipEP4?si=GIZI73RzJZy1B_cj)
---
### Google, Microsoft and AWS has their own courses ( you can pick the one where you want to start)
### OpenAI has really good [documentation](https://platform.openai.com/docs/introduction) and [Cookbook](https://cookbook.openai.com/)
## Youtube ( Free University )
- There is unlimited knoweledge you can grasp, try to find the best ones and follow them instead of jumping among videos.
- Main thing is to understand things and try it yourself. Unless you try (practice youself), you won't learn.
- I have videos on LLMs with playlist on langchain, chainlit and Llamaindex. Many LLMs videos to follow in 2024
- [Langchain playlist](https://youtube.com/playlist?list=PLz-qytj7eIWVd1a5SsQ1dzOjVDHdgC1Ck&si=UsnrzCA1kUsYLtLe)
- [LlamaIndex playlist](https://youtube.com/playlist?list=PLz-qytj7eIWWqLRAJh-Q_fuvs0qH739zz&si=ljn51QFH4qbFL3uz)
---
> Main thing I want to highlight, practice practice and practice, take help with AI assistants 👇
## AI Assistants ( Remember, personal use or enterprise use )
- [Perplexity AI](https://perplexity.ai/pro?referral_code=YAWB6JNV) --> let's put this way, it's Google Search with LLMs with it.
- [Perplexity Labs, For Open Source models](https://labs.perplexity.ai/)
- [ChatGPT](https://chat.openai.com/) --> Based on your need, free or paid version. ( Team, Enterprise , etc)
- [Bing Chat](https://www.bing.com/search?q=Bing+AI&showconv=1&FORM=hpcodx) , Bing Enterprise.
- [Hugging Chat](https://huggingface.co/chat/)
- [Le Chat Mistral](https://chat.mistral.ai)
---
## Make RAG work properly
- First, think on tweeking basic stuffs
- Cleaning document ( choose right parsing , eg. LlamaParse, Unstructured )
- Better Chunking strategies
- Choosing right embeddings model
- Choosing right Vectorstore
- Passing parsing Instructions, Reranking
- Choosing right Large Language Models
Links to follow for better understanding.
- [Chunk visualizer](https://huggingface.co/spaces/m-ric/chunk_visualizer)
- [Tokenizer, from OpenAI](https://platform.openai.com/tokenizer)
- [Huggingface Massive Text Embedding Benchmark (MTEB) Leaderboard](https://huggingface.co/spaces/mteb/leaderboard)
- [What is a Vector Database & How Does it Work? Use Cases + Examples](https://www.pinecone.io/learn/vector-database/)
- [Chunking Strategies for LLM Applications](https://www.pinecone.io/learn/chunking-strategies/)
- [🤗 Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
- [🏆 LMSYS Chatbot Arena Leaderboard](https://chat.lmsys.org/)
- [12 RAG Pain Points and Proposed Solutions](https://towardsdatascience.com/12-rag-pain-points-and-proposed-solutions-43709939a28c)
- [Optimizing RAG with Hybrid Search & Reranking](https://superlinked.com/vectorhub/optimizing-rag-with-hybrid-search-and-reranking)
- [Improving RAG performance with Knowledge Graphs](https://superlinked.com/vectorhub/improving-rag-performance-with-knowledge-graphs)
- [Enhancing RAG with a Multi-Agent System](https://superlinked.com/vectorhub/enhancing-rag-with-a-multi-agent-system)
-----
## Important Links Updated ( 22 August 2024 )
- [Llama-3-Groq-Tool-Use Models](https://wow.groq.com/introducing-llama-3-groq-tool-use-models/)
- [Berkeley Funciton Calling Leaderboard](https://gorilla.cs.berkeley.edu/leaderboard.html#leaderboard)
- [Independent analysis of AI models and API providers](https://artificialanalysis.ai/) :pushpin:
----
## Important Links Updated ( 02 September 2024 )
### AWS
- [Evaluating RAG applications with Amazon Bedrock knowledge base evaluation](https://aws.amazon.com/blogs/machine-learning/evaluating-rag-applications-with-amazon-bedrock-knowledge-base-evaluation/)
- [AWS Samples](https://github.com/aws-samples)
----
- [LangChain Azure Integration](https://devblogs.microsoft.com/azure-sql/langchain-with-sqlvectorstore/)
- [RAG vs Agentic RAG](https://www.analyticsvidhya.com/blog/2024/11/rag-vs-agentic-rag/)
- [Comphrensive Guide in RAG Implementation](https://newsletter.armand.so/p/comprehensive-guide-rag-implementations)
----
### RAG and Agents
- [RAG_Techniques](https://github.com/NirDiamant/RAG_Techniques)
- [GenAI Agents](https://github.com/NirDiamant/GenAI_Agents)
----
- [2024-AI-Timeline Huggingface Space](https://huggingface.co/spaces/reach-vb/2024-ai-timeline)
---
### LLM Docs
- [Anthropic Docs](https://docs.anthropic.com/en/home)
- [OpenAI Docs](https://platform.openai.com/docs/overview)
### Model Context Protocol
- [All about MCP](https://modelcontextprotocol.io/introduction)
- [MCP announcement from Claude](https://www.anthropic.com/news/model-context-protocol)
- [Claude for Desktop](https://claude.ai/download)
- [Claude code](https://docs.anthropic.com/en/docs/agents-and-tools/claude-code/overview)
- [Good blog post about Intro to MCP](https://blog.aitoolhouse.com/introduction-to-the-model-context-protocol-mcp-a-developers-guide-to-the-mcp-for-smarter-ai-assistants/)
- [Offical Github MCP Servers](https://github.com/modelcontextprotocol/servers)
- [Awesome MCP Servers](https://github.com/punkpeye/awesome-mcp-servers)
- [What is MCP, and Why Is Everyone Suddenly Talking About It](https://huggingface.co/blog/Kseniase/mcp)
- [MCP server Directory](https://www.pulsemcp.com/servers)
- [Awesome MCP Servers and Clients](https://mcp.so/)
- [FastMCP](https://gofastmcp.com/getting-started/welcome)
- [What is Model Context Protocol (MCP)? How it simplifies AI integrations compared to APIs](https://norahsakal.com/blog/mcp-vs-api-model-context-protocol-explained/#when-are-traditional-apis-better)
- [Open Source MCP Servers, Glama.ai](https://glama.ai/mcp/servers)
- [MCP Inspector, Visual testing tool for MCP servers](https://github.com/modelcontextprotocol/inspector)
### Leaked System Prompts
- [Leaked system prompts](https://github.com/jujumilk3/leaked-system-prompts)
> Cheers !!
Last Updated: February 2025