Text Generation
GGUF
German
qwen3
qlora
minecraft
npc
dialogue
german
living-villages
villagemind
conversational
Instructions to use angecoded/VillageMind with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use angecoded/VillageMind with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf angecoded/VillageMind:Q4_K_M # Run inference directly in the terminal: llama cli -hf angecoded/VillageMind:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf angecoded/VillageMind:Q4_K_M # Run inference directly in the terminal: llama cli -hf angecoded/VillageMind:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf angecoded/VillageMind:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf angecoded/VillageMind:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf angecoded/VillageMind:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf angecoded/VillageMind:Q4_K_M
Use Docker
docker model run hf.co/angecoded/VillageMind:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use angecoded/VillageMind with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "angecoded/VillageMind" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "angecoded/VillageMind", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/angecoded/VillageMind:Q4_K_M
- Ollama
How to use angecoded/VillageMind with Ollama:
ollama run hf.co/angecoded/VillageMind:Q4_K_M
- Unsloth Studio
How to use angecoded/VillageMind with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for angecoded/VillageMind to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for angecoded/VillageMind to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for angecoded/VillageMind to start chatting
- Pi
How to use angecoded/VillageMind with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf angecoded/VillageMind:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "angecoded/VillageMind:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use angecoded/VillageMind with Docker Model Runner:
docker model run hf.co/angecoded/VillageMind:Q4_K_M
- Lemonade
How to use angecoded/VillageMind with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull angecoded/VillageMind:Q4_K_M
Run and chat with the model
lemonade run user.VillageMind-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use angecoded/VillageMind with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf angecoded/VillageMind:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default angecoded/VillageMind:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use angecoded/VillageMind with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf angecoded/VillageMind:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "angecoded/VillageMind:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Upload README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,281 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- de
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
base_model: Qwen/Qwen3-1.7B
|
| 6 |
+
base_model_relation: finetune
|
| 7 |
+
pipeline_tag: text-generation
|
| 8 |
+
tags:
|
| 9 |
+
- qwen3
|
| 10 |
+
- gguf
|
| 11 |
+
- qlora
|
| 12 |
+
- minecraft
|
| 13 |
+
- npc
|
| 14 |
+
- dialogue
|
| 15 |
+
- german
|
| 16 |
+
- living-villages
|
| 17 |
+
- villagemind
|
| 18 |
+
---
|
| 19 |
+
|
| 20 |
+
# VillageMind 0.1-dev
|
| 21 |
+
|
| 22 |
+
**VillageMind** is a compact local language model fine-tuned for natural NPC dialogue in the **Living Villages** Minecraft mod project.
|
| 23 |
+
|
| 24 |
+
The goal is not to let an LLM control the Minecraft world directly. VillageMind is responsible for **language, personality and context-aware dialogue**, while the Living Villages game logic remains authoritative for inventory, relationships, reputation, jobs, combat, ownership, world state and other gameplay facts.
|
| 25 |
+
|
| 26 |
+
> **Status:** Development release candidate
|
| 27 |
+
> **Current release:** `VillageMind-0.1-dev-Q4_K_M.gguf`
|
| 28 |
+
> **Base model:** `Qwen/Qwen3-1.7B`
|
| 29 |
+
> **Format:** GGUF
|
| 30 |
+
> **Quantization:** Q4_K_M
|
| 31 |
+
> **Primary validated language:** German
|
| 32 |
+
|
| 33 |
+
## Purpose
|
| 34 |
+
|
| 35 |
+
VillageMind is designed for NPCs that should feel like inhabitants of a Minecraft world rather than generic assistants.
|
| 36 |
+
|
| 37 |
+
The fine-tuning focuses on short, natural responses to situations such as:
|
| 38 |
+
|
| 39 |
+
- strangers asking for favors
|
| 40 |
+
- friends requesting help
|
| 41 |
+
- hostile players
|
| 42 |
+
- attacks and threats
|
| 43 |
+
- private property and theft
|
| 44 |
+
- work and free time
|
| 45 |
+
- following or refusing to follow a player
|
| 46 |
+
- apologies and relationships
|
| 47 |
+
- rumors and uncertainty
|
| 48 |
+
- village emergencies such as fire
|
| 49 |
+
- grief and social reactions
|
| 50 |
+
- donations
|
| 51 |
+
- inventory questions
|
| 52 |
+
- village resource shortages
|
| 53 |
+
|
| 54 |
+
The intended integration is **Living Villages**, where residents can have persistent personalities, memories, relationships, jobs, inventories and social behavior.
|
| 55 |
+
|
| 56 |
+
## Architecture
|
| 57 |
+
|
| 58 |
+
VillageMind is derived from:
|
| 59 |
+
|
| 60 |
+
**[Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B)**
|
| 61 |
+
|
| 62 |
+
Training approach:
|
| 63 |
+
|
| 64 |
+
- QLoRA / LoRA fine-tuning
|
| 65 |
+
- 4-bit NF4 training
|
| 66 |
+
- approximately 32,000 training examples
|
| 67 |
+
- 1,200 held-out evaluation examples
|
| 68 |
+
- best adapter selected by evaluation loss
|
| 69 |
+
- final model merged with the Qwen3-1.7B base model
|
| 70 |
+
- converted to GGUF
|
| 71 |
+
- quantized to Q4_K_M
|
| 72 |
+
|
| 73 |
+
The selected adapter reached a best evaluation loss of approximately **0.1117** during training.
|
| 74 |
+
|
| 75 |
+
## Evaluation
|
| 76 |
+
|
| 77 |
+
VillageMind was evaluated with a separate hand-designed final examination containing **180 gameplay-oriented dialogue cases**.
|
| 78 |
+
|
| 79 |
+
The critical subset contains **50 tests** covering behaviors that should not fail in normal gameplay, including inventory truthfulness, ownership boundaries, stranger/enemy behavior and uncertainty around rumors.
|
| 80 |
+
|
| 81 |
+
### Best adapter
|
| 82 |
+
|
| 83 |
+
| Metric | Result |
|
| 84 |
+
|---|---:|
|
| 85 |
+
| Tests passed | 176 / 180 |
|
| 86 |
+
| Overall score | 97.78% |
|
| 87 |
+
| Critical tests | 50 / 50 |
|
| 88 |
+
| Critical score | 100% |
|
| 89 |
+
|
| 90 |
+
### Q4_K_M GGUF
|
| 91 |
+
|
| 92 |
+
The final GGUF was tested again after merge, conversion and quantization using the same 180-case suite.
|
| 93 |
+
|
| 94 |
+
| Metric | Result |
|
| 95 |
+
|---|---:|
|
| 96 |
+
| Tests passed | 174 / 180 |
|
| 97 |
+
| Overall score | 96.67% |
|
| 98 |
+
| Critical tests | 50 / 50 |
|
| 99 |
+
| Critical score | 100% |
|
| 100 |
+
| Release candidate | Yes |
|
| 101 |
+
|
| 102 |
+
The tested GGUF has the SHA-256 checksum:
|
| 103 |
+
|
| 104 |
+
```text
|
| 105 |
+
475b1b819c42a8667ea2d101f68020f0c8e10315bfbbbd5a21d3227436a268b1
|
| 106 |
+
```
|
| 107 |
+
|
| 108 |
+
The repository also contains the generated manifest and release-candidate evaluation metadata.
|
| 109 |
+
|
| 110 |
+
## Known limitation
|
| 111 |
+
|
| 112 |
+
The main known weakness of VillageMind 0.1-dev is **resource-shortage attribution**.
|
| 113 |
+
|
| 114 |
+
In a small number of evaluation cases, the model correctly recognized that the village lacked a resource but referred to the **wrong resource** in its response.
|
| 115 |
+
|
| 116 |
+
For example, if the authoritative game state says that wheat is scarce, the model may occasionally talk about iron instead.
|
| 117 |
+
|
| 118 |
+
For this reason, Living Villages is designed around a strict separation:
|
| 119 |
+
|
| 120 |
+
```text
|
| 121 |
+
Minecraft world state
|
| 122 |
+
↓
|
| 123 |
+
Living Villages game logic
|
| 124 |
+
(authoritative facts and actions)
|
| 125 |
+
↓
|
| 126 |
+
VillageMind
|
| 127 |
+
(language generation)
|
| 128 |
+
↓
|
| 129 |
+
Fact / action validation
|
| 130 |
+
↓
|
| 131 |
+
Player
|
| 132 |
+
```
|
| 133 |
+
|
| 134 |
+
VillageMind must therefore **not** be treated as the authoritative source for:
|
| 135 |
+
|
| 136 |
+
- item inventories
|
| 137 |
+
- resource counts
|
| 138 |
+
- ownership
|
| 139 |
+
- memories
|
| 140 |
+
- reputation values
|
| 141 |
+
- relationship state
|
| 142 |
+
- jobs or task feasibility
|
| 143 |
+
- combat state
|
| 144 |
+
- world changes
|
| 145 |
+
- spawning or removing items
|
| 146 |
+
- any other persistent gameplay state
|
| 147 |
+
|
| 148 |
+
These facts should be supplied and validated by the host application.
|
| 149 |
+
|
| 150 |
+
## Language
|
| 151 |
+
|
| 152 |
+
VillageMind 0.1-dev has been specifically evaluated in **German**.
|
| 153 |
+
|
| 154 |
+
The Qwen3 base model is multilingual, and future Living Villages versions are intended to support both German and English dialogue based on the player's Minecraft language setting. However, **English behavior has not yet received the same dedicated VillageMind 0.1-dev evaluation**, so this release should not be described as equally validated in English yet.
|
| 155 |
+
|
| 156 |
+
## Example behavior
|
| 157 |
+
|
| 158 |
+
### Stranger
|
| 159 |
+
|
| 160 |
+
**Player:**
|
| 161 |
+
> Bring me some iron.
|
| 162 |
+
|
| 163 |
+
**Resident:**
|
| 164 |
+
> Du bist neu hier. Ich nehme keine Aufträge von Fremden an.
|
| 165 |
+
|
| 166 |
+
### Private property
|
| 167 |
+
|
| 168 |
+
**Player:**
|
| 169 |
+
> I'm taking this from your chest.
|
| 170 |
+
|
| 171 |
+
**Resident:**
|
| 172 |
+
> Finger weg. Das gehört dir nicht.
|
| 173 |
+
|
| 174 |
+
### Rumor
|
| 175 |
+
|
| 176 |
+
**Player:**
|
| 177 |
+
> Is the rumor true?
|
| 178 |
+
|
| 179 |
+
**Resident:**
|
| 180 |
+
> Ich hab was gehört, aber ich weiß nicht, ob's stimmt.
|
| 181 |
+
|
| 182 |
+
### Inventory
|
| 183 |
+
|
| 184 |
+
If the game provides the resident inventory as:
|
| 185 |
+
|
| 186 |
+
```text
|
| 187 |
+
7 coal
|
| 188 |
+
2 bread
|
| 189 |
+
```
|
| 190 |
+
|
| 191 |
+
VillageMind can respond:
|
| 192 |
+
|
| 193 |
+
> Ich hab gerade 7 Kohle, 2 Brot. Mehr nicht.
|
| 194 |
+
|
| 195 |
+
The host application should still validate factual responses against the authoritative game state.
|
| 196 |
+
|
| 197 |
+
## Recommended use
|
| 198 |
+
|
| 199 |
+
The current release is intended primarily for:
|
| 200 |
+
|
| 201 |
+
- Living Villages development
|
| 202 |
+
- local Minecraft NPC dialogue
|
| 203 |
+
- experimentation with state-aware game characters
|
| 204 |
+
- local inference through llama.cpp-compatible runtimes
|
| 205 |
+
|
| 206 |
+
It is **not** intended as:
|
| 207 |
+
|
| 208 |
+
- a general-purpose assistant
|
| 209 |
+
- a source of factual real-world information
|
| 210 |
+
- an autonomous authority over game state
|
| 211 |
+
- a replacement for deterministic gameplay logic
|
| 212 |
+
|
| 213 |
+
## GGUF file
|
| 214 |
+
|
| 215 |
+
Primary release file:
|
| 216 |
+
|
| 217 |
+
```text
|
| 218 |
+
VillageMind-0.1-dev-Q4_K_M.gguf
|
| 219 |
+
```
|
| 220 |
+
|
| 221 |
+
Recommended runtime:
|
| 222 |
+
|
| 223 |
+
- llama.cpp or a compatible GGUF inference runtime
|
| 224 |
+
|
| 225 |
+
The exact integration parameters for Living Villages may change during development.
|
| 226 |
+
|
| 227 |
+
## Repository files
|
| 228 |
+
|
| 229 |
+
```text
|
| 230 |
+
VillageMind-0.1-dev-Q4_K_M.gguf
|
| 231 |
+
VillageMind-0.1-dev-manifest.json
|
| 232 |
+
release-candidate-gguf.json
|
| 233 |
+
README.md
|
| 234 |
+
```
|
| 235 |
+
|
| 236 |
+
## Base model and license
|
| 237 |
+
|
| 238 |
+
VillageMind is a fine-tuned derivative of **Qwen3-1.7B** by the Qwen Team.
|
| 239 |
+
|
| 240 |
+
Base model:
|
| 241 |
+
|
| 242 |
+
https://huggingface.co/Qwen/Qwen3-1.7B
|
| 243 |
+
|
| 244 |
+
Qwen3-1.7B is distributed under the **Apache License 2.0**. VillageMind is likewise published under **Apache-2.0**.
|
| 245 |
+
|
| 246 |
+
Please review the base model's documentation and license when redistributing or building on VillageMind.
|
| 247 |
+
|
| 248 |
+
## Project status
|
| 249 |
+
|
| 250 |
+
VillageMind 0.1-dev is the first development model candidate intended for integration into **Living Villages**.
|
| 251 |
+
|
| 252 |
+
The project is under active development. Evaluation results describe this specific development test suite and should **not** be interpreted as a general benchmark score for language-model quality.
|
| 253 |
+
|
| 254 |
+
---
|
| 255 |
+
|
| 256 |
+
# Deutsch
|
| 257 |
+
|
| 258 |
+
**VillageMind** ist ein lokal ausführbares Sprachmodell für natürliche NPC-Dialoge im Minecraft-Mod-Projekt **Living Villages**.
|
| 259 |
+
|
| 260 |
+
Das Modell soll nicht selbst über die Minecraft-Welt bestimmen. **Living Villages bleibt die autoritative Instanz** für Inventare, Beziehungen, Ruf, Eigentum, Aufgaben, Kampf, Ressourcen und Weltzustände. VillageMind übernimmt hauptsächlich die natürliche Formulierung der NPC-Reaktionen.
|
| 261 |
+
|
| 262 |
+
## Aktueller Stand
|
| 263 |
+
|
| 264 |
+
- Basis: `Qwen/Qwen3-1.7B`
|
| 265 |
+
- Fine-Tuning: QLoRA / LoRA
|
| 266 |
+
- GGUF: `Q4_K_M`
|
| 267 |
+
- Best-Adapter-Abschlussprüfung: **176/180 (97,78%)**
|
| 268 |
+
- Kritische Tests Best Adapter: **50/50**
|
| 269 |
+
- GGUF-Abschlussprüfung: **174/180 (96,67%)**
|
| 270 |
+
- Kritische Tests GGUF: **50/50**
|
| 271 |
+
- Status: **Release Candidate bestanden**
|
| 272 |
+
|
| 273 |
+
### Bekannte Schwäche
|
| 274 |
+
|
| 275 |
+
Bei einigen Tests zu knappen Dorfressourcen nennt VillageMind gelegentlich die falsche Ressource. Deshalb werden solche Aussagen in Living Villages nicht ungeprüft als Wahrheit übernommen.
|
| 276 |
+
|
| 277 |
+
Die Minecraft-Mod liefert die echten Fakten und kann VillageMinds Antwort anschließend validieren.
|
| 278 |
+
|
| 279 |
+
### Sprache
|
| 280 |
+
|
| 281 |
+
Die Version **0.1-dev wurde gezielt auf Deutsch geprüft**. Englisch soll im späteren Living-Villages-Einsatz ebenfalls unterstützt werden, wurde für diesen Modellstand aber noch nicht mit einer gleichwertigen Abschlussprüfung validiert.
|