text stringlengths 0 90 |
|---|
<b>🧙 WIZARD STATUS: |
Tradition: Frostweaver (Level 1) |
❤️ HP: 93/93 (100%) |
💙 MP: 73/73 (100%) |
State: ✓ AWAKE |
🐦 FAMILIAR STATUS: |
Type: Shadow Cat (Level 1) |
❤️ HP: 117/117 (100%) |
State: ✓ AWAKE |
💝 Bond: 99/100 |
👾 CAVE DWELLERS: |
1. Troll Cavern Stalker |
✓ ACTIVE (33/33 HP) |
💰 VISIBLE TREASURE: mithril ore, orcish spirits, glowcap mushroom |
🎒 INVENTORY: |
• Stamina Brew x3 |
• Lantern x1 |
• Iron Key x1 |
• Mana Elixir x1 |
• Healing Draught x3 |
• Scroll of Flame x1 |
🎮 AVAILABLE CHOICES: |
1. Attack the weakest enemy |
2. Cast area-of-effect spell (Fire Blast) |
3. Command familiar to attack |
4. Cast Blinding Snow (ice AoE) |
5. Use a healing draught |
6. Use a mana elixir |
7. Cast Mystic Barrier (protective buff) |
8. Wait and observe |
❓ What is your choice? (Enter the number) |
<eot> |
<h>Tradition: Frostweaver (Level 1) |
❤️ HP: 93/93 (100%) |
💙 MP: 73/73 (100%) |
State: ✓ AWAKE |
🐦 FAMILIAR STATUS: |
Type: Shadow Cat (Level 1) |
❤️ HP: 105/117 (89%) |
State: ✓ AWAKE |
💝 Bond: 100/100 |
👾 CAVE DWELLERS: |
1. Troll Cavern Stalker |
✓ ACTIVE (9/33 HP) |
💰 VISIBLE TREASURE: mithril ore, orcish spirits, glowcap mushroom |
I choose option 3 (Command familiar to attack) my familiar is ready to fight. |
🎯 ATTACKED: |
• Troll Cavern Stalker (via familiar) |
<eot> |
<b>You chose: Command familiar to attack |
• Your Shadow Cat familiar attacks Troll for 27 damage (reduced by defense to 24)! |
Familiar bond increases to 100. |
Enemy HP: 9/33 |
🔄 ENEMY COUNTER-ATTACKS: |
• Troll attacks your familiar for 12 damage. (Enemy base damage: 9) |
Familiar HP: 105/117 |
🎯 ENTITIES ATTACKED THIS TURN: |
• Troll Cavern Stalker (via familiar) |
📊 UPDATED STATUS: |
Wizard: 93/93 HP, 73/73 MP |
Wizard State: ✓ AWAKE |
Familiar: 105/117 HP, State: ✓ AWAKE, Bond: 100 |
Familiar damage taken: 12 |
Enemies remaining: 1 |
<eot> |
<b>🧙 WIZARD STATUS: |
Tradition: Frostweaver (Level 1) |
❤️ HP: 93/93 (100%) |
💙 MP: 73/73 (100%) |
State: ✓ AWAKE |
🐦 FAMILIAR STATUS: |
Type: Shadow Cat (Level 1) |
❤️ HP: 105/117 (89%) |
State: ✓ AWAKE |
💝 Bond: 100/100 |
✨ Familiar Effects: Familiar Critical! (Bond bonus) |
👾 CAVE DWELLERS: |
1. Troll Cavern Stalker |
✓ ACTIVE (9/33 HP) |
💰 VISIBLE TREASURE: mithril ore, orcish spirits, glowcap mushroom |
End of preview. Expand
in Data Studio
YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/datasets-cards)
name: magician-mud-conversations pretty_name: Magician MUD Conversations description: 20 turn-by-turn gameplay conversations from a text-based dungeon crawler RPG (MUD style). Each conversation captures strategic decision-making in fantasy combat, including player status, enemy encounters, resource management, and combat outcomes. Ideal for fine-tuning language models for RPG dialogue generation, tactical decision-making, and game state understanding. license: cc-by-sa-4.0 languages:
- en multilinguality: monolingual size_categories: n<1K source_datasets:
- original annotations_creators:
- machine-generated language_creators:
- machine-generated tags:
- rpg
- game-ai
- tactical-decision-making
- fantasy
- mud
- conversations
- turn-based-combat task_categories:
- text-generation
- text2text-generation task_ids:
- dialogue-generation
- text-simplification
- language-modeling homepage: https://huggingface.co/datasets/magician-mud-conversations dataset_size: 500 splits: train: 400 validation: 50 test: 50 dataset_structure: description: Each instance represents a single conversation turn. fields: conversation_id: string game_id: string turn_number: int speaker: string message: string game_state: dict selected_choice: string choice_number: int choice_reason: string attacked_entities: list combat_outcome: dict game_outcome: string considerations: social_impact: Fantasy violence only; no real-world sensitive content. bias: > Contains combat-focused scenarios in a Western fantasy RPG setting. AI choices may not reflect human player behavior. limitations: > Small dataset (500 conversations). Synthetic data, domain-specific. Not suitable for large-scale pre-training. recommended_use_cases:
- Fine-tuning small to medium language models (≤7B parameters)
- Training supervised game-playing agents
- RPG dialogue systems
- Tactical AI research
- Game design education not_recommended_use_cases:
- Large-scale pre-training
- Real-world decision-making systems
- Medical, financial, or safety-critical applications citation: bibtex: | @dataset{magician-mud-conversations-2025, title = {Magician MUD Conversations: A Dataset of 500 Tactical RPG Dialogues}, author = {Magician MUD Simulator Team}, year = {2025}, publisher = {Hugging Face}, version = {1.0.0}, url = {https://huggingface.co/datasets/RPG_DM_Simulation_Combat_LLM_Training} }
Get the full dataset on Gumroad at https://datadeveloper1.gumroad.com/l/lmfhbg
- Downloads last month
- 8