Datasets:

arman-bd
/

guppylm-60k-generic

license: mit
task_categories:
  - text-generation
language:
  - en
size_categories:
  - 10K<n<100K
tags:
  - fish
  - character
  - tiny-llm
  - synthetic
pretty_name: GuppyLM Chat

GuppyLM

GuppyLM Chat Dataset

Training data for GuppyLM — a ~9M parameter LLM that talks like a small fish.

Dataset Description

60K single-turn conversations between a human and Guppy, a small fish character. Guppy speaks in short, lowercase sentences about water, food, light, and tank life. It doesn't understand human abstractions.

Example

Input:  are you hungry
Output: yes. always yes. i will swim to the top right now.

Input:  what do you think about politics
Output: i don't know what politics is. is it wet.

Input:  goodnight guppy
Output: night. i'll rest near the bottom. maybe tomorrow there will be pellets.

Fields

Field	Type	Description
`input`	string	User message
`output`	string	Guppy's response
`category`	string	Topic category (60 categories)

Categories

Greetings, feelings, temperature (hot/cold), food, light, water, about, confused (human things), tank, noise, night, lonely, misc, goodbye, bubbles, glass, reflection, breathing, swimming, colors, taste, plants, filter, algae, snail, glass tapping, scared, excited, bored, curious, happy, tired, outside, cat, rain, seasons, music, visitors, children, meaning of life, time, memory, dreams, size, future, past, name, weather, sleep, friends, jokes, fear, love, age, intelligence, bathroom, health, singing, TV.

Usage

from datasets import load_dataset
ds = load_dataset("arman-bd/guppylm-60k-generic")
print(ds["train"][0])
# {'input': 'hi guppy', 'output': 'hello. the water is nice today.', 'category': 'greeting'}

Generation

Data is synthetically generated using template composition with randomized components (tank objects, food types, activities, body parts, etc.) for high output diversity.

License

MIT