Instructions to use ws-fy/character-model-showcase with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ws-fy/character-model-showcase 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 ws-fy/character-model-showcase:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ws-fy/character-model-showcase:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ws-fy/character-model-showcase:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ws-fy/character-model-showcase:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf ws-fy/character-model-showcase:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf ws-fy/character-model-showcase:Q4_K_M

Use Docker

docker model run hf.co/ws-fy/character-model-showcase:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use ws-fy/character-model-showcase with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ws-fy/character-model-showcase"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ws-fy/character-model-showcase",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ws-fy/character-model-showcase:Q4_K_M

Ollama
How to use ws-fy/character-model-showcase with Ollama:
```
ollama run hf.co/ws-fy/character-model-showcase:Q4_K_M
```
Unsloth Desktop

How to use ws-fy/character-model-showcase with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ws-fy/character-model-showcase:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ws-fy/character-model-showcase:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ws-fy/character-model-showcase with Docker Model Runner:
```
docker model run hf.co/ws-fy/character-model-showcase:Q4_K_M
```

Lemonade

How to use ws-fy/character-model-showcase with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ws-fy/character-model-showcase:Q4_K_M

Run and chat with the model

lemonade run user.character-model-showcase-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use ws-fy/character-model-showcase with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ws-fy/character-model-showcase: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 ws-fy/character-model-showcase:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ws-fy/character-model-showcase with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ws-fy/character-model-showcase: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 "ws-fy/character-model-showcase: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"

Character Model Showcase

English · 跳转到中文版 →

About

A personal collection of character role-play models I fine-tuned for my own use. Each character lives in its own folder, and comes in three forms: the LoRA adapter, the merged full model, and GGUF quantizations.

These are style adapters rather than knowledge models — the goal is to make a general model speak in a particular character's voice (tone, word choice, verbal tics), not to reproduce official setting material. A character card / system prompt is required for best results.

Path	What it is
`Kafka/lora/`	LoRA adapter for Qwen3.5-9B (r=16, alpha=32). Includes a text-only key-remapped copy in `adapter_text_only/`
`Kafka/merged/`	The adapter merged into the base model, FP16
`Kafka/gguf/`	GGUF builds: BF16, Q8_0, Q4_K_M, Q2_0, Q1_0

Disclaimer

This is a personal hobby project. It is not affiliated with, endorsed by, or supported by the original rights holders of any character or franchise referenced here.
Provided for personal study, research and entertainment only. Please do not use it commercially, and do not use it to impersonate real people or to mislead anyone.
Outputs are generated by a language model and may be inaccurate, out of character, or inappropriate. Nothing it produces should be treated as fact, advice, or official canon.
The base model's own license applies in addition to this notice. If you are a rights holder and would like something removed, please contact me and I will take it down.

中文版

↑ 回到英文

简介

这里是我个人训练的角色扮演模型合集，每个角色一个文件夹，提供三种形态：LoRA 适配器、合并后的完整模型、以及 GGUF 量化版。

这些是风格适配器，不是知识模型 —— 目的是让通用模型用某个角色的口吻（语气、用词、口癖）说话，而不是复现官方设定。使用时配合角色卡 / system prompt 效果最好。

内容

路径	说明
`Kafka/lora/`	Qwen3.5-9B 的 LoRA 适配器（r=16，alpha=32）；`adapter_text_only/` 是改好纯文本键名的副本
`Kafka/merged/`	适配器与基座合并后的 FP16 完整模型
`Kafka/gguf/`	GGUF 量化：BF16、Q8_0、Q4_K_M、Q2_0、Q1_0

免责声明

本项目为个人兴趣作品，与任何角色或作品的权利方无关联，也未获其认可或支持。
仅供个人学习、研究与娱乐使用。请勿用于商业用途，也请勿用于冒充真实人物或误导他人。
输出由语言模型生成，可能不准确、不符合角色设定或内容不当，不应被视为事实、建议或官方设定。
基座模型自身的许可条款同样适用。若您是权利方并希望下架相关内容，请联系我处理。

Downloads last month: 548

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

1-bit

2-bit

4-bit

8-bit

16-bit

Model tree for ws-fy/character-model-showcase

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Adapter

(1020)

this model

ws-fy
/

character-model-showcase

Character Model Showcase

About

Contents

Disclaimer

中文版

简介

内容

免责声明

Model tree for ws-fy/character-model-showcase