Instructions to use cyanelis/ElisNovel-V1-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cyanelis/ElisNovel-V1-14B with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("cyanelis/ElisNovel-V1-14B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use cyanelis/ElisNovel-V1-14B 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 cyanelis/ElisNovel-V1-14B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf cyanelis/ElisNovel-V1-14B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf cyanelis/ElisNovel-V1-14B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf cyanelis/ElisNovel-V1-14B: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 cyanelis/ElisNovel-V1-14B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf cyanelis/ElisNovel-V1-14B: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 cyanelis/ElisNovel-V1-14B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cyanelis/ElisNovel-V1-14B:Q4_K_M

Use Docker

docker model run hf.co/cyanelis/ElisNovel-V1-14B:Q4_K_M

LM Studio
Jan
Ollama
How to use cyanelis/ElisNovel-V1-14B with Ollama:
```
ollama run hf.co/cyanelis/ElisNovel-V1-14B:Q4_K_M
```

Unsloth Studio

How to use cyanelis/ElisNovel-V1-14B 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 cyanelis/ElisNovel-V1-14B 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 cyanelis/ElisNovel-V1-14B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cyanelis/ElisNovel-V1-14B to start chatting

How to use cyanelis/ElisNovel-V1-14B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cyanelis/ElisNovel-V1-14B: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": "cyanelis/ElisNovel-V1-14B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use cyanelis/ElisNovel-V1-14B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cyanelis/ElisNovel-V1-14B: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 cyanelis/ElisNovel-V1-14B:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use cyanelis/ElisNovel-V1-14B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cyanelis/ElisNovel-V1-14B: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 "cyanelis/ElisNovel-V1-14B: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"

Docker Model Runner
How to use cyanelis/ElisNovel-V1-14B with Docker Model Runner:
```
docker model run hf.co/cyanelis/ElisNovel-V1-14B:Q4_K_M
```

Lemonade

How to use cyanelis/ElisNovel-V1-14B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cyanelis/ElisNovel-V1-14B:Q4_K_M

Run and chat with the model

lemonade run user.ElisNovel-V1-14B-Q4_K_M

List all available models

lemonade list

ElisNovel-V1-14B

本模型基于Qwen3-14B，专门用于小说文本续写（完美穿透朱雀检测，AI率为0）。

安装方式（以ollama为例）

更新ollama(如果是window则右键upgrade即可)：

curl -fsSL https://ollama.com/install.sh | sh

快速安装{

ollama run cyanelis/ElisNovel-V1:14b # 从ollama模型库安装Q4_K_M精度，预计占用显存12G-

快速安装的模型名称默认为：cyanelis/ElisNovel-V1:14b

}

手动安装{

下载gguf模型文件：

windows下载链接：https://hf-mirror.com/cyanelis/ElisNovel-V1-14B/resolve/main/ElisNovel-V1-14B-Q4_K_M.gguf

linux输入：wget "https://hf-mirror.com/cyanelis/ElisNovel-V1-14B/resolve/main/ElisNovel-V1-14B-Q4_K_M.gguf?download=true" -O ElisNovel-V1-14B-Q4_K_M.gguf

下载modelfile文件：

windows下载链接：https://hf-mirror.com/cyanelis/ElisNovel-V1-14B/resolve/main/Modelfile

linux输入：wget "https://hf-mirror.com/cyanelis/ElisNovel-V1-14B/resolve/main/Modelfile?download=true" -O Modelfile

进入它们所在的同一个目录，输入以下命令：

ollama create ElisNovel-V1-14B-Q4_K_M -f Modelfile # 安装Q4_K_M精度，预计占用显存12G-

如将上述手动安装中的Q4_K_M（也包括Modelfile文件的第四行中的Q4_K_M）都改为Q8_0或F16，则会安装Q8_0或F16精度，预计显存占用18G-/28G

手动安装的模型名称默认为：ElisNovel-V1-14B-你选择的精度:latest

}

使用方式

ollama serve # 启动ollama。windows双击ollama运行也行。

最大上下文长度不低于但最好等于5770tokens：

/set parameter num_ctx 5770 # 每次run一个模型之后输入。下个版本会写进modelfile里。

清空系统级提示词。

输入不超过4320字（2880tokens）的内容，模型预测4320字下文。

批量推理简单脚本————你完全可以将其魔改成适合你的版本{

windows下载链接：https://hf-mirror.com/cyanelis/ElisNovel-V1-14B/resolve/main/tokenzzzsimple.py

linux输入：wget "https://hf-mirror.com/cyanelis/ElisNovel-V1-14B/resolve/main/tokenzzzsimple.py?download=true" -O tokenzzzsimple.py

需要把txt文件放入G109b文件夹（没有则新建一个），G109b文件夹内的第一个文件推理得到Z109c\Z2.txt，第二个文件推理得到Z109c\Z3.txt，最后一个文件推理得到Z109c\Z1.txt

再开一个终端/命令提示符：

python tokenzzzsimple.py # 假设模型名称为cyanelis/ElisNovel-V1:14b

}

注意事项⚠️

请遵守apache-2.0。
生成内容的传播需符合当地法律法规。
模型生成内容的文风取决于输入内容的文风，会尽量贴近。
模型在不知道大纲的前提下进行续写，续写方向根据输入的内容的趋势进行预测。
小说所需要的逻辑对于目前的模型而言负担太大，生成内容不宜直接使用，因此需要人类智慧的校正。

信息反馈

交流群：755638032

Downloads last month: 497

GGUF

Model size

15B params

Architecture

qwen3

Hardware compatibility

4-bit

8-bit

16-bit

Inference Providers NEW

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

Model tree for cyanelis/ElisNovel-V1-14B

Base model

Qwen/Qwen3-14B-Base

Finetuned

Qwen/Qwen3-14B

Quantized

(200)

this model