# LLM

AI Language Model (LLM) Agents are advanced machine learning models that have been trained on a diverse range of internet text. They can generate human-like text based on the input they receive. However, they do not understand the text they generate and do not have beliefs, opinions, or consciousness. These agents are designed to assist users in generating text for a variety of purposes, such as drafting emails, writing code, creating written content, tutoring in a variety of subjects, translating languages, simulating characters for video games, and much more.

**Resources for understanding LLM from scratch :-**

1. [Neural Networks: Zero to Hero - YouTube](https://www.youtube.com/playlist?list=PLAqhIrjkxbuWI23v9cThsA9GvCAUhRvKZ) \[Andrej Karpathy]
2. [Building LLMs from scratch - YouTube](https://www.youtube.com/playlist?list=PLPTV0NXA_ZSgsLAr8YCgCwhPIJNNtexWu)
3. [Build DeepSeek from Scratch](https://www.youtube.com/playlist?list=PLPTV0NXA_ZSiOpKKlHCyOq9lnp-dLvlms)
4. <https://www.youtube.com/playlist?list=PLPTV0NXA_ZSiOpKKlHCyOq9lnp-dLvlms>
5. [LLM from Scratch Tutorial – Code & Train Qwen 3](https://www.youtube.com/watch?v=Jaj_SQsF-BI\&list=LL\&index=1\&pp=gAQBiAQB)
6. <https://www.youtube.com/watch?v=UU1WVnMk4E8>
7. [LLMs: Understanding Temperature and Context Length of a GPT](https://www.youtube.com/watch?v=IllijoYSH80)
8. <https://www.youtube.com/watch?v=lrWY4O5kUTY&list=LL&index=30&pp=gAQBiAQBsAgC>
9. <https://www.youtube.com/watch?v=p3sij8QzONQ>&#x20;
10. [https://www.vizuaranewsletter.com/p/introduction-to-vlms](<https://www.vizuaranewsletter.com/p/introduction-to-vlms&#xA;https://www.vizuaranewsletter.com/p/why-do-we-need-transformers-for-vision&#xA;https://www.vizuaranewsletter.com/p/coding-a-vision-transformer-almost?utm_source=publication-search&#xA;>)
11. [https://www.vizuaranewsletter.com/p/why-do-we-need-transformers-for-vision](<https://www.vizuaranewsletter.com/p/introduction-to-vlms&#xA;https://www.vizuaranewsletter.com/p/why-do-we-need-transformers-for-vision&#xA;https://www.vizuaranewsletter.com/p/coding-a-vision-transformer-almost?utm_source=publication-search&#xA;>)
12. [https://www.vizuaranewsletter.com/p/coding-a-vision-transformer-almost?utm\_source=publication-search<br>](<https://www.vizuaranewsletter.com/p/introduction-to-vlms&#xA;https://www.vizuaranewsletter.com/p/why-do-we-need-transformers-for-vision&#xA;https://www.vizuaranewsletter.com/p/coding-a-vision-transformer-almost?utm_source=publication-search&#xA;>)

Link for Study on LLM Agents

* \[ ][ https://www.promptingguide.ai/research/llm-agents](https://www.promptingguide.ai/research/llm-agents)
* \[ ][ https://medium.com/@aydinKerem/what-is-an-llm-agent-and-how-does-it-work-1d4d9e4381ca](https://medium.com/@aydinKerem/what-is-an-llm-agent-and-how-does-it-work-1d4d9e4381ca)
* \[ ][ https://medium.com/the-modern-scientist/a-complete-guide-to-llms-based-autonomous-agents-part-i-69515c016792](https://medium.com/the-modern-scientist/a-complete-guide-to-llms-based-autonomous-agents-part-i-69515c016792)
* \[ ][ https://lilianweng.github.io/posts/2023-06-23-agent/](https://lilianweng.github.io/posts/2023-06-23-agent/)
* \[ ][ https://github.com/kaushikb11/awesome-llm-agents](https://github.com/kaushikb11/awesome-llm-agents)
* \[ ][ https://www.youtube.com/watch?v=0pnEUAwoDP0](https://www.youtube.com/watch?v=0pnEUAwoDP0)
* \[ ][ https://www.youtube.com/watch?v=fo0F-DAum7E](https://www.youtube.com/watch?v=fo0F-DAum7E)
* \[ ][ https://www.youtube.com/watch?v=v1tyQtncsE4](https://www.youtube.com/watch?v=v1tyQtncsE4)
* \[ ][ https://gorilla.cs.berkeley.edu/](https://gorilla.cs.berkeley.edu/)
* \[ ][ https://cookbook.openai.com/](https://cookbook.openai.com/)
* <https://langroid.github.io/langroid/>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://59r.gitbook.io/ml-university/natural-language-processing/llm.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.