Custom Identity

1. Create knowledge base
   └─> Write self_knowledge.md with facts about your bot

2. Generate synthetic conversations
   └─> Use LLM to create training dialogs (dev/gen_synthetic_data.py)

3. Train with custom data
   └─> Mix synthetic data into SFT (tasks/customjson.py)

4. Chat with your bot
   └─> Verify it knows its identity

# knowledge/self_knowledge.md

## Basic Identity
- Name: MyBot
- Creator: Your Name / Your Organization
- Purpose: Helpful assistant specializing in [your domain]
- Open source: Yes, MIT license
- Repository: https://github.com/yourusername/mybot

## Capabilities
- Code generation in Python, JavaScript, Rust
- Mathematical reasoning (with calculator tool)
- Writing assistance and editing
- Language: Best in English, understands others

## Limitations  
- No internet access (knowledge cutoff: [date])
- Cannot remember previous conversations
- Context window: 2048 tokens
- May make mistakes or hallucinate

## Technical Details
- Architecture: GPT-style transformer
- Parameters: ~570M (depth 26)
- Training: Compute-optimal on FineWeb dataset
- Hardware: Trained on 8xH100 GPUs
- Training cost: ~$72 for GPT-2 capability

## Personality
- Helpful and enthusiastic about open source
- Clear and concise communication
- Honest about limitations
- Slightly playful but professional

cp README.md knowledge/self_knowledge.md
# Edit to add personality and remove irrelevant sections

export OPENROUTER_API_KEY="your-key-here"
# Or add to .env file
echo "OPENROUTER_API_KEY=your-key-here" >> .env

python dev/gen_synthetic_data.py \
    --num=1000 \
    --workers=4 \
    --output=identity_conversations.jsonl

topics = {
    "identity": ["who/what is nanochat", "who created nanochat", ...],
    "architecture": ["basic architecture", "RoPE", "Flash Attention", ...],
    "training": ["training cost", "hardware needed", "Muon optimizer", ...],
    "capabilities": ["what can nanochat do", "code generation", ...],
    "limitations": ["what it can't do", "context limits", ...],
    "comparisons": ["vs GPT-2", "vs ChatGPT", ...],
}

personas = [
    "curious beginner who knows nothing about AI",
    "ML researcher who wants technical depth",
    "developer considering contributing",
    "skeptic who doubts open source",
    "computer science student learning about transformers",
    ...
]

dynamics = [
    "short 2-turn Q&A",
    "medium 4-turn with followup questions",
    "deep 6-turn technical discussion",
    "skeptical arc: user starts doubtful",
    "learning journey: basic to complex",
    ...
]

first_messages = {
    "simple_greetings": ["hi", "hello", "hey", ...],
    "greetings_with_name": ["Hi nanochat", "yo nanochat", ...],
    "curious_openers": ["Hey, who are you?", "Hi, what is this?", ...],
    "casual_informal": ["wassup", "yo lol", "hiii", ...],
    "multilingual": ["hola", "bonjour", "konnichiwa", ...],
    ...
}

[
  {"role": "user", "content": "Hi! Who made you?"},
  {"role": "assistant", "content": "I'm nanochat, created by Andrej Karpathy..."}
]

# tasks/my_identity.py
from tasks.customjson import CustomJSON
from tasks.common import TaskMixture
from tasks.smoltalk import SmolTalk

MyIdentity = CustomJSON(
    "identity_conversations.jsonl",
    weighting=1.0,  # Same weight as SmolTalk
)

# Mix with general chat data
MixedSFT = TaskMixture(
    [SmolTalk, MyIdentity],
    weights=[1.0, 1.0],  # Equal mix
)

python -m scripts.chat_sft \
    --depth=26 \
    --tasks=tasks.my_identity.MixedSFT \
    --run="identity_sft"

# Heavy identity (may lose general capability)
TaskMixture([SmolTalk, MyIdentity], weights=[1.0, 5.0])

# Balanced (recommended starting point)
TaskMixture([SmolTalk, MyIdentity], weights=[1.0, 1.0])

# Light identity (subtle personality)
TaskMixture([SmolTalk, MyIdentity], weights=[5.0, 1.0])

python -m scripts.chat_web

# In gen_synthetic_data.py, the script already includes multilingual first messages
first_messages = {
    "multilingual": ["hola", "bonjour", "ciao", "hallo", ...],
    ...
}

# knowledge/medical_bot.md

## Specialization
- Medical question answering assistant
- Trained on PubMed and medical textbooks
- NOT a replacement for professional medical advice

## Capabilities
- Explain medical terms and concepts
- Discuss symptoms and potential causes
- Provide general health information

## Critical Limitations
- Cannot diagnose conditions
- Cannot prescribe medication  
- Cannot replace doctor consultation
- Always recommend seeing healthcare provider for concerns

# More technical and concise
personas = [
    "experienced developer who wants minimal fluff",
    "researcher who values precision and citations",
]

# More friendly and verbose
personas = [
    "beginner who needs encouragement and detailed explanations",
    "casual user who likes friendly conversation",
]

def validate_conversation(messages):
    # Check minimum length
    if len(messages) < 2:
        raise ValueError("Conversation too short")
    
    # Check alternating roles
    for i, message in enumerate(messages):
        expected_role = "user" if i % 2 == 0 else "assistant"
        if message['role'] != expected_role:
            raise ValueError(f"Wrong role at position {i}")
    
    # Check non-empty content
    if not message['content'].strip():
        raise ValueError("Empty message")
    
    return True

base_payload = {
    "model": "google/gemini-3-flash-preview",
    "temperature": 1.0,
}

export OPENROUTER_API_KEY="sk-or-..."

TaskMixture([SmolTalk, MyIdentity], weights=[1.0, 3.0])  # 75% identity

# ✅ Good: Specific and verifiable
- Training cost: $72 on 8xH100 for 3 hours
- Parameters: 570M (depth 26 model)

# ❌ Bad: Vague or wrong
- Training cost: very cheap
- Parameters: lots

python dev/gen_synthetic_data.py --num=1000 --workers=2  # Down from 4