llm-basics

# LLM Basics

Master the fundamentals of Large Language Models.

## Quick Start

### Using OpenAI API
```python
from openai import OpenAI

client = OpenAI()

response = client.chat.completions.create(
    model="gpt-4",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain transformers briefly."}
    ],
    temperature=0.7,
    max_tokens=500
)

print(response.choices[0].message.content)
```

### Using Hugging Face
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_name = "meta-llama/Llama-2-7b-hf"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

inputs = tokenizer("Hello, how are", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=50)
print(tokenizer.decode(outputs[0]))
```

## Core Concepts

### Transformer Architecture
```
Input → Embedding → [N × Transformer Block] → Output

Transformer Block:
┌───────────────────────────┐
│ Multi-Head Self-Attention │
├───────────────────────────┤
│   Layer Normalization     │
├───────────────────────────┤
│   Feed-Forward Network    │
├───────────────────────────┤
│   Layer Normalization     │
└───────────────────────────┘
```

### Tokenization
```python
from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("gpt2")
text = "Hello, world!"

# Encode
tokens = tokenizer.encode(text)
print(tokens)  # [15496, 11, 995, 0]

# Decode
decoded = tokenizer.decode(tokens)
print(decoded)  # "Hello, world!"
```

### Key Parameters
```python
# Generation parameters
params = {
    'temperature': 0.7,      # Randomness (0-2)
    'max_tokens': 1000,      # Output length limit
    'top_p': 0.9,            # Nucleus sampling
    'top_k': 50,             # Top-k sampling
    'frequency_penalty': 0,  # Reduce repetition
    'presence_penalty': 0    # Encourage new topics
}
```

## Model Comparison

| Model | Parameters | Con