There is a new training script for this release. The responses are shorter in the "improved" datasets.

The model was trained on a zero-shot Alpaca instruction format:

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{system prompt}

### Input:
User: Wait a minute.

Assistant: Assistant's heart skipped a beat, she hadn't expected to meet anyone today.

User: Hey, didn't I see you at the library yesterday?

Traits: Shy

Length: Short

### Response:

After several attempts, I have decided not to support multi-turn conversation for the time being. You can use labels (traits, length) to control the assistant's behavior before the response field.

Datasets about unexpected events:

Datasets about personality traits:

Datasets by response length:

There are more than 100 of them in the datasets.

Affectionate, Afraid, Aggressive, Alarmed, Alert, Ambitious, Amiable, Amorous, Amused, Angry, Annoyed, Anxious, Apathetic, Apologetic, Argumentative, Aroused, Arrogant, Ashamed, Assertive, Astonished, Attentive, Bellicosity, Bitter, Bluntness, Bored, Calm, Capriciousness, Caring, Cautious, Compassionate, Competitive, Concerned, Confident, Confused, Content, Courageous, Creative, Critical, Cruelty, Curious, Defiant, Depressed, Desperate, Despondent, Determined, Disappointed, Disgusted, Disobedient, Dissatisfied, Doubtful, Efficient, Embarrassed, Empathetic, Encouraging, Enthusiastic, Envious, Excited, Exhausted, Expectant, Fidelity, Forgetful, Forgiving, Fragility, Friendly, Frugal, Frustrated, Generous, Grateful, Guilty, Happy, Hateful, Helpful, Helpless, Hesitant, Homesick, Honest, Hopeful, Hostile, Impatient, Impulsive, Indecisive, Indignant, Insecure, Insulted, Integrity, Interested, Jealous, Joyous, Kind, Kindness, Loathing, Longing, Loquacity, Lost, Loving, Loyal, Lusting, Miserable, Motivated, Nervous, Nostalgic, Optimistic, Organized, Passionate, Patient, Pensive, Persistent, Persuasive, Playful, Pleased, Polite, Protective, Proud, Rebellious, Relaxed, Relieved, Remorseful, Resilient, Restless, Reverent, Sad, Scared, Self-critical, Selfish, Sentimental, Serene, Serious, Shy, Shyness, Sleepy, Startled, Stubbornness, Superior, Supportive, Suspicious, Sympathetic, Tender, Tense, Thoughtful, Tired, Understanding, Upset, Wisdom, Worried.

Scherer KR. What are emotions? And how can they be measured?

MIT An Affective Model of Interplay Between Emotions and Learning

Scherer KR. The GRID meets the wheel

Manshad Abbasi Mohsin Summarizing Emotions from Text Using Plutchik’s Wheel of Emotions