# LLM - Day 1 - Intro

> Source: <https://dev.to/technonotes/llm-day-1-lets-learn-ai-4p9l>
> Published: 2026-09-17 19:19:41+00:00

## 
  
  
  Large Language Model

- Its a model
- what is a model ? its a equation.
- Then what is equation ? y = mx + c or y = m1x2 + m2x3 + m3x2
- Models are nothing but WEIGHTS.
- Take an example Eg: gpt-oss-120b , for this model they would have used data with TRANSFORMER ARCHITECTURE and we are getting some output that is called MODEL.
m --> weights ( we can adjust the m and get many desierd outputs )

- Model is floating point storage.
- சில பேரு சொல்லுவாங்க இது வந்து 120B Paramter model , what it means ? These Parameters are nothing but how many weights I am having inside the model.
நான் எந்த அளவுக்கு dataவை கொடுத்து train பண்ணி இருக்கேன்னு அர்த்தம். In other words , CONTEXT அதிகம் .
- Can we run this 120B Paramter in machine ? 
--> Where the OS sits ? C drive or /boot , initially it will be in hard disc , once the machine starts , it will go to RAM Running memory போய் உட்கார்ந்து கொல்லும். So to run the model we need RAM and also the CPU , so these two decides which model to run. Eg., in laptop we can run 7B parameter.
- In local like laptop we can run eg., llama cpp, ollama , LM Studio . இது எல்லாம் modelஆ ? No , these are softwares/tools to run the model.
- Open model are called like " Open weights model ". Eg., chatgpt model , gemini model. ( Referring to Open source )

**Why I Need a model ?**

1. LLM is a next word predictor.
Eg., Hi How ......... இதுக்கப்புறம் என்ன வரலாம் like are you , is your life , is the food . இது எல்லாம் ஒரு possibilities ( It can have n no of possibilites ).
MORE THE PRESENCE , MORE POSSIBILITY OF OCCURING.
நீங்க ஒரு வார்த்தையை குடுக்குறீங்க , அதுக்கு அடுத்த வார்த்தை இது கண்டுபிடித்து தர போது . Then this will go as input , like wise it will generate.
2. All each possibilities will have SCORE , entire score will like between [ 0 - 100 ] or [ 0 - 1 ] . 
3. If you are not giving any controlling parameter , then it will chose the highest SCORE.
4. If you want to control the LLM , at that place . We have controlling parameters. Namely :

*Temparature*

1. 0-1
2. controls how random or safe the model choices.
3. If the TEMP is low like ( 0-0.3 ) then it will ACT BASED ON THE FACTS. Likely having max score / most occuring one.
4. If the TEMP is high like ( 0.7 - 1+ ) , model is willing to choice less likely words. Eg., in storing telling or in creating writing. It will choose less likely words from dataset which is trained on.

*Top-k*

1. Along with temperature its used.
2. Model only considers , Top k most items. 
3. K --> Elements

*Top-P*

1. Also its called Sampling methods.
2. It will add the score and then it will work.
3. Along with temperature its used.

இப்ப Top - pகு 90 % value  சொல்லிட்டாங்க .  இப்ப அது எப்படி work ஆகும் நா. Each prediction will have a score eg., first prediction  0.70 ,  அடுத்த prediction 0.15 , அடுத்த prediction 0.30 . It will add the prediction score which is equal to 90 % ( more or less ) இத வச்சு தான் அந்த output கொடுக்கும்.

**Tokens**

1. words ?
2. which are " Not complete ".
3. Entire text into pieces.
4. Tokenization ? Process of chopping your text into tokens.
5. Each token will be assigned numbers.
6. Take it like a translator. 

**Context Window**

1. Model ஓட short memory.
2. Short term memory.
3. Max of tokens a model can see in a given time.
4. ஒரு timeல  ஒரு model லால , எவ்வளவு விஷயத்தை பார்க்க முடியும்.

**TBD  :**

1. What is dataset ?
2. Chunkings ?

**Notes :**

1. If I am going to use a model , then I need to unzip it , for this i need a running memory so we need RAM. Now , i need process the data , then CPU & GPU ( training a& usage ) are required.
2. Weigts will be like FOLATING POINTS or EMBEDDINGS.
3. 
[https://groq.com/](https://groq.com/) --> Its a tool --> They give free models for usage.

1. Fine Tuning is not updating the model or touching the weights. We use like rapper around the model thats called Fine Tunning.
2. Markov Chain --> this is used in next word prediction in gmail , word etc .
3. Harry Porter and context window .