Instructions to use walter-bd/npc-voice-soup06 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use walter-bd/npc-voice-soup06 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="walter-bd/npc-voice-soup06",
	filename="gguf/npc-voice-soup06.Q5_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use walter-bd/npc-voice-soup06 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf walter-bd/npc-voice-soup06:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf walter-bd/npc-voice-soup06:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf walter-bd/npc-voice-soup06:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf walter-bd/npc-voice-soup06:Q5_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 walter-bd/npc-voice-soup06:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf walter-bd/npc-voice-soup06:Q5_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 walter-bd/npc-voice-soup06:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf walter-bd/npc-voice-soup06:Q5_K_M

Use Docker

docker model run hf.co/walter-bd/npc-voice-soup06:Q5_K_M

LM Studio
Jan
Ollama
How to use walter-bd/npc-voice-soup06 with Ollama:
```
ollama run hf.co/walter-bd/npc-voice-soup06:Q5_K_M
```

Unsloth Studio

How to use walter-bd/npc-voice-soup06 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 walter-bd/npc-voice-soup06 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 walter-bd/npc-voice-soup06 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for walter-bd/npc-voice-soup06 to start chatting

How to use walter-bd/npc-voice-soup06 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf walter-bd/npc-voice-soup06:Q5_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": "walter-bd/npc-voice-soup06:Q5_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use walter-bd/npc-voice-soup06 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf walter-bd/npc-voice-soup06:Q5_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 walter-bd/npc-voice-soup06:Q5_K_M

Run Hermes

hermes

Docker Model Runner
How to use walter-bd/npc-voice-soup06 with Docker Model Runner:
```
docker model run hf.co/walter-bd/npc-voice-soup06:Q5_K_M
```

Lemonade

How to use walter-bd/npc-voice-soup06 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull walter-bd/npc-voice-soup06:Q5_K_M

Run and chat with the model

lemonade run user.npc-voice-soup06-Q5_K_M

List all available models

lemonade list

NPC Voice Model — soup-0.6 (Best)

Best performing model in the NPC voice series. A weight-averaged merge of v5-SFT (60%) and v5-DPO (40%), fine-tuned on Qwen3-0.6B.

The model takes a plain factual sentence and rewrites it in a character's voice, conditioned on 6 persona parameters.

Why soup-0.6?

SFT alone generates some verbatim copies and quote-wrapping failures. DPO alone over-corrects and forgets rare relation types. Weight averaging (model soup) gives the best of both: DPO's structural fixes + SFT's coverage.

Model	Pass	Halluc fail	Fact pres	EN	ES
v4	59.0%	32.5%	1.31	66%	50%
v5-SFT	60.0%	29.6%	1.39	68%	44%
v5-DPO	57.0%	36.0%	1.26	69%	40%
soup-0.6	61.5%	28.5%	1.42	75%	44%

Task

INPUT:  TONE:grumpy STYLE:blunt HUMOR:none RELATION:stranger ROLE:blacksmith
        FACT: Iron swords cost 15 gold.
OUTPUT: Fifteen gold. Don't haggle.

Parameters

Param	Values
TONE	grumpy, cheerful, neutral, fearful, proud, bitter, nervous, wise, cunning, melancholic, playful
STYLE	short, verbose, blunt, rambling, poetic
HUMOR	none, dry, sarcastic, warm, dark
RELATION	stranger, friend, enemy, ally, rival, mentor, debtor, heretic, worshipper, + 20 more
ROLE	blacksmith, innkeeper, guard, merchant, peasant, scholar, noble, priest

Only RELATION changes at runtime based on game state. The other 4 are fixed per NPC at config time.

Inference (Python)

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    "walter-bd/npc-voice-soup06",
    max_seq_length=256,
)
FastLanguageModel.for_inference(model)

prompt = "TONE:grumpy STYLE:blunt HUMOR:none RELATION:stranger ROLE:blacksmith\nFACT: Iron swords cost 15 gold.\nOUT:"
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
out = model.generate(**inputs, max_new_tokens=80, temperature=0.7, do_sample=True)
print(tokenizer.decode(out[0], skip_special_tokens=True).split("OUT:")[-1].strip())

GGUF / Ollama

Note: ollama run hf.co/walter-bd/npc-voice-soup06:Q5_K_M will trigger Qwen3 thinking mode. Use the custom Modelfile below to suppress it and use the correct raw prompt format.

# Download GGUF and Modelfile
wget https://huggingface.co/walter-bd/npc-voice-soup06/resolve/main/gguf/npc-voice-soup06.Q5_K_M.gguf
wget https://huggingface.co/walter-bd/npc-voice-soup06/resolve/main/Modelfile

# Create local model with thinking suppressed
ollama create npc-voice-soup06 -f Modelfile

# Run
ollama run npc-voice-soup06 "TONE:grumpy STYLE:blunt HUMOR:none RELATION:stranger ROLE:blacksmith
FACT: Iron swords cost 15 gold.
OUT:"

How it was built

v5-SFT — LoRA fine-tune on ~35k bilingual rows with targeted weak-slot coverage
v5-DPO — Direct Preference Optimization using 1,195 real model failure pairs as rejected examples
soup-0.6 — 0.6 x v5-SFT + 0.4 x v5-DPO weight average

Dataset: walter-bd/npc-voice-dataset Code: github.com/walter-bd/small-persona-llm

Downloads last month: 41

Safetensors

Model size

0.6B params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for walter-bd/npc-voice-soup06

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Adapter

(413)

this model