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 3 days ago

Commit

da9ffa4

verified ·

1 Parent(s): 41f0de9

Upload V3.8/README.de.md with huggingface_hub

Browse files

Files changed (1) hide show

V3.8/README.de.md +2 -2

V3.8/README.de.md CHANGED Viewed

@@ -35,7 +35,7 @@ pipeline_tag: text-generation
 - [3. Versionshinweise](#3-versionshinweise)
 - [4. Kernkompetenzen](#4-kernkompetenzen)
 - [5. Technische Spezifikationen](#5-technische-spezifikationen)
-- [6. ⚡ Schnellstart](#6--schnellstart-3-dateien--100--beste-inferenz) — **3-Dateien-Paket**
 - [7. Modell-Downloads](#7-modell-downloads)
 - [8. Startbefehle](#8-startbefehle)
 - [9. Empfohlene Inferenzparameter](#9-empfohlene-inferenzparameter)
@@ -135,7 +135,7 @@ MoziAI hält einen aktiven Upgrade-Rhythmus, bleibt an der Spitze der KI-Entwick
 ---
-## 6. ⚡ Schnellstart 3 Dateien = 100 % beste Inferenz
 > ⚠️ **Wichtig**: Für die beste Inferenz müssen **3 Dateien zusammen** heruntergeladen werden — Hauptmodell, Vision-Projektor, Chat-Template. Fehlt eine, geht die entsprechende Fähigkeit verloren.

 - [3. Versionshinweise](#3-versionshinweise)
 - [4. Kernkompetenzen](#4-kernkompetenzen)
 - [5. Technische Spezifikationen](#5-technische-spezifikationen)
+- [6. Schnellstart](#6-schnellstart-3-dateien-100-beste-inferenz) — **3-Dateien-Paket**
 - [7. Modell-Downloads](#7-modell-downloads)
 - [8. Startbefehle](#8-startbefehle)
 - [9. Empfohlene Inferenzparameter](#9-empfohlene-inferenzparameter)
 ---
+## 6. Schnellstart 3 Dateien 100 beste Inferenz
 > ⚠️ **Wichtig**: Für die beste Inferenz müssen **3 Dateien zusammen** heruntergeladen werden — Hauptmodell, Vision-Projektor, Chat-Template. Fehlt eine, geht die entsprechende Fähigkeit verloren.