Instructions to use chenyumo/moziAI-35B-A3B-MOE-MTP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use chenyumo/moziAI-35B-A3B-MOE-MTP 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 chenyumo/moziAI-35B-A3B-MOE-MTP:BF16
# Run inference directly in the terminal:
llama cli -hf chenyumo/moziAI-35B-A3B-MOE-MTP:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf chenyumo/moziAI-35B-A3B-MOE-MTP:BF16
# Run inference directly in the terminal:
llama cli -hf chenyumo/moziAI-35B-A3B-MOE-MTP:BF16

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 chenyumo/moziAI-35B-A3B-MOE-MTP:BF16
# Run inference directly in the terminal:
./llama-cli -hf chenyumo/moziAI-35B-A3B-MOE-MTP:BF16

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 chenyumo/moziAI-35B-A3B-MOE-MTP:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf chenyumo/moziAI-35B-A3B-MOE-MTP:BF16

Use Docker

docker model run hf.co/chenyumo/moziAI-35B-A3B-MOE-MTP:BF16

LM Studio
Jan

vLLM

How to use chenyumo/moziAI-35B-A3B-MOE-MTP with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chenyumo/moziAI-35B-A3B-MOE-MTP"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chenyumo/moziAI-35B-A3B-MOE-MTP",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/chenyumo/moziAI-35B-A3B-MOE-MTP:BF16

Ollama
How to use chenyumo/moziAI-35B-A3B-MOE-MTP with Ollama:
```
ollama run hf.co/chenyumo/moziAI-35B-A3B-MOE-MTP:BF16
```
Unsloth Desktop

How to use chenyumo/moziAI-35B-A3B-MOE-MTP with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf chenyumo/moziAI-35B-A3B-MOE-MTP:BF16

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": "chenyumo/moziAI-35B-A3B-MOE-MTP:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use chenyumo/moziAI-35B-A3B-MOE-MTP with Docker Model Runner:
```
docker model run hf.co/chenyumo/moziAI-35B-A3B-MOE-MTP:BF16
```

Lemonade

How to use chenyumo/moziAI-35B-A3B-MOE-MTP with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull chenyumo/moziAI-35B-A3B-MOE-MTP:BF16

Run and chat with the model

lemonade run user.moziAI-35B-A3B-MOE-MTP-BF16

List all available models

lemonade list

Hermes Agent

How to use chenyumo/moziAI-35B-A3B-MOE-MTP with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf chenyumo/moziAI-35B-A3B-MOE-MTP:BF16

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 chenyumo/moziAI-35B-A3B-MOE-MTP:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use chenyumo/moziAI-35B-A3B-MOE-MTP with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf chenyumo/moziAI-35B-A3B-MOE-MTP:BF16

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 "chenyumo/moziAI-35B-A3B-MOE-MTP:BF16" \
  --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"

chenyumo commited on 4 days ago

Commit

89526fd

verified ·

1 Parent(s): 583f59e

Upload MODEL_CARD.md with huggingface_hub

Browse files

Files changed (1) hide show

MODEL_CARD.md +5 -3

MODEL_CARD.md CHANGED Viewed

@@ -64,10 +64,12 @@ Supports llama.cpp, Ollama, LM Studio, Jan and other mainstream inference framew
 | Platform | URL |
 | --- | --- |
-| HuggingFace | [chenyumo/moziAI-35B-A3B-MOE-MTP](https://huggingface.co/chenyumo/moziAI-35B-A3B-MOE-MTP) |
-| ModelScope | [chenyumo/moziAI-35B-A3B-MOE-MTP](https://modelscope.cn/models/chenyumo/moziAI-35B-A3B-MOE-MTP) |
-| GitHub | [chenyumo166/moziAI-35B](https://github.com/chenyumo166/moziAI-35B-A3B-MOE-MTP) |
 | Ollama | `ollama pull chenyumo/moziAI-35B-A3B` |
 > ⚠️ **3-file tip**: download all files in the `V3.8/` directory — main model (.gguf), vision projector (mmproj), chat template (.jinja) — into the same folder for 100% best inference.

 | Platform | URL |
 | --- | --- |
+| HuggingFace | [https://huggingface.co/chenyumo/moziAI-35B-A3B-MOE-MTP](https://huggingface.co/chenyumo/moziAI-35B-A3B-MOE-MTP) |
+| ModelScope | [https://modelscope.cn/models/chenyumo/moziAI-35B-A3B-MOE-MTP](https://modelscope.cn/models/chenyumo/moziAI-35B-A3B-MOE-MTP) |
+| GitHub | [https://github.com/chenyumo166/moziAI-35B-A3B-MOE-MTP](https://github.com/chenyumo166/moziAI-35B-A3B-MOE-MTP) |
+| GitCode | [https://ai.gitcode.com/chenyumo166/moziAI-35B-A3B-MOE-MTP](https://ai.gitcode.com/chenyumo166/moziAI-35B-A3B-MOE-MTP) |
 | Ollama | `ollama pull chenyumo/moziAI-35B-A3B` |
+| LM Studio | Search `moziAI` in LM Studio → Download |
 > ⚠️ **3-file tip**: download all files in the `V3.8/` directory — main model (.gguf), vision projector (mmproj), chat template (.jinja) — into the same folder for 100% best inference.