Instructions to use NovaAI6868/BaiHu-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use NovaAI6868/BaiHu-gguf 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 NovaAI6868/BaiHu-gguf:F16
# Run inference directly in the terminal:
llama cli -hf NovaAI6868/BaiHu-gguf:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf NovaAI6868/BaiHu-gguf:F16
# Run inference directly in the terminal:
llama cli -hf NovaAI6868/BaiHu-gguf:F16

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 NovaAI6868/BaiHu-gguf:F16
# Run inference directly in the terminal:
./llama-cli -hf NovaAI6868/BaiHu-gguf:F16

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 NovaAI6868/BaiHu-gguf:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NovaAI6868/BaiHu-gguf:F16

Use Docker

docker model run hf.co/NovaAI6868/BaiHu-gguf:F16

LM Studio
Jan

vLLM

How to use NovaAI6868/BaiHu-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NovaAI6868/BaiHu-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NovaAI6868/BaiHu-gguf",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/NovaAI6868/BaiHu-gguf:F16

Ollama
How to use NovaAI6868/BaiHu-gguf with Ollama:
```
ollama run hf.co/NovaAI6868/BaiHu-gguf:F16
```

Unsloth Studio

How to use NovaAI6868/BaiHu-gguf 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 NovaAI6868/BaiHu-gguf 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 NovaAI6868/BaiHu-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NovaAI6868/BaiHu-gguf to start chatting

How to use NovaAI6868/BaiHu-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NovaAI6868/BaiHu-gguf:F16

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": "NovaAI6868/BaiHu-gguf:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use NovaAI6868/BaiHu-gguf with Docker Model Runner:
```
docker model run hf.co/NovaAI6868/BaiHu-gguf:F16
```

Lemonade

How to use NovaAI6868/BaiHu-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NovaAI6868/BaiHu-gguf:F16

Run and chat with the model

lemonade run user.BaiHu-gguf-F16

List all available models

lemonade list

Hermes Agent

How to use NovaAI6868/BaiHu-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NovaAI6868/BaiHu-gguf:F16

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 NovaAI6868/BaiHu-gguf:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use NovaAI6868/BaiHu-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NovaAI6868/BaiHu-gguf:F16

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 "NovaAI6868/BaiHu-gguf:F16" \
  --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"

NovaAI6868 commited on Jun 22

Commit

4fda437

verified ·

1 Parent(s): 5093fa0

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +8 -9

README.md CHANGED Viewed

@@ -1,6 +1,6 @@
 ---
 language: zh
-license: other
 tags:
   - multimodal
   - vision
@@ -21,7 +21,6 @@ pipeline_tag: image-text-to-text
 ## 模型简介
 - **模型名称**: 白虎-v2
-- **架构**: `Gemma4ForConditionalGeneration`
 - **上下文长度**: 131,072 tokens
 - **词表大小**: 262,144
 - **数据类型**: float16
@@ -35,11 +34,11 @@ pipeline_tag: image-text-to-text
 | 文件 | 说明 |
 |------|------|
-| `白虎-v2.Q4_K_M.gguf` | 主模型 GGUF 量化版本（Q4_K_M），适合本地 CPU/GPU 推理 |
-| `白虎-v2.F16-mmproj.gguf` | 多模态投影层（mmproj）FP16 版本，配合主模型用于图像/音频/视频理解 |
 | `Modelfile` | llama.cpp / Ollama 的模型配置文件示例 |
-> 推荐搭配使用：`白虎-v2.Q4_K_M.gguf` + `白虎-v2.F16-mmproj.gguf`
 ---
@@ -60,7 +59,7 @@ pipeline_tag: image-text-to-text
 参考仓库中的 `Modelfile` 创建 Ollama 模型：
 ```bash
-ollama create 白虎-v2 -f Modelfile
 ollama run 白虎-v2
 ```
@@ -68,8 +67,8 @@ ollama run 白虎-v2
 ```bash
 ./llama-cli \
-  -m 白虎-v2.Q4_K_M.gguf \
-  --mmproj 白虎-v2.F16-mmproj.gguf \
   --image example.jpg \
   -p "请描述这张图片："
 ```
@@ -105,7 +104,7 @@ ollama run 白虎-v2
 ## 授权协议
-使用本模型前请仔细阅读并遵守相关许可协议条款。
 ---

 ---
 language: zh
+license: mit
 tags:
   - multimodal
   - vision
 ## 模型简介
 - **模型名称**: 白虎-v2
 - **上下文长度**: 131,072 tokens
 - **词表大小**: 262,144
 - **数据类型**: float16
 | 文件 | 说明 |
 |------|------|
+| `BaiHu-v2.Q4_K_M.gguf` | 主模型 GGUF 量化版本（Q4_K_M），适合本地 CPU/GPU 推理 |
+| `BaiHu-v2.F16-mmproj.gguf` | 多模态投影层（mmproj）FP16 版本，配合主模型用于图像/音频/视频理解 |
 | `Modelfile` | llama.cpp / Ollama 的模型配置文件示例 |
+> 推荐搭配使用：`BaiHu-v2.Q4_K_M.gguf` + `BaiHu-v2.F16-mmproj.gguf`
 ---
 参考仓库中的 `Modelfile` 创建 Ollama 模型：
 ```bash
+ollama create BaiHu-v2 -f Modelfile
 ollama run 白虎-v2
 ```
 ```bash
 ./llama-cli \
+  -m BaiHu-v2.Q4_K_M.gguf \
+  --mmproj BaiHu-v2.F16-mmproj.gguf \
   --image example.jpg \
   -p "请描述这张图片："
 ```
 ## 授权协议
+本模型采用 **MIT 协议** 开源。使用本模型前请仔细阅读并遵守 MIT 许可协议条款。
 ---