Instructions to use FriskyFennec/Ling-3.0-tiny-base-midtrain-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 FriskyFennec/Ling-3.0-tiny-base-midtrain-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 FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF: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 FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF: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 FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF:Q4_K_M

Use Docker

docker model run hf.co/FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FriskyFennec/Ling-3.0-tiny-base-midtrain-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": "FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF:Q4_K_M

Ollama
How to use FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF with Ollama:
```
ollama run hf.co/FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF:Q4_K_M
```
Unsloth Desktop

How to use FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF: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": "FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF with Docker Model Runner:
```
docker model run hf.co/FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF:Q4_K_M
```

Lemonade

How to use FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Ling-3.0-tiny-base-midtrain-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use FriskyFennec/Ling-3.0-tiny-base-midtrain-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 FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF: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 FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF: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 "FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF: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"

Ling-3.0-tiny-base-midtrain

A GGUF variant of inclusionAI's Ling-3.0-tiny-base-midtrain model, suitable for base/foundational model experiments and text completion use cases.

The model was converted & quantized using llama.cpp's build 0.4.0-dev.

Examples

Running via llama.cpp

Model's tested with,

llama-server.exe --model Ling-3.0-tiny-base-midtrain-BF16.gguf --ctx-size 8192 --gpu-layers 256 --main-gpu 0 --flash-attn auto --mlock --timeout 600 --host 127.0.0.1 --port 8080

Output

Samplers:

Temperature: 0.7
Top P: 0.95
Top K: 40
Repetition Penalty: 1.1
Repetition Penalty Range: 256

Input,

Once upon a time,

Output 1,

 there lived two little birds who were brother and sister. They had the most beautiful voices. Their parents were also very musical. And so, they were taught to sing from the day they could talk and walk.
When they grew up, their parents

Output 2,

 in the bustling city of Toronto, Canada, there lived a young and enthusiastic journalist named John. Known for his sharp wit and unwavering dedication to uncovering the truth behind every story, John had earned a reputation as one of the best investigative reporters in the industry

Output 3,

 there was a girl named Alice who fell down a rabbit hole and found herself in a world of strange creatures. This whimsical tale is a classic story that has captivated readers for generations.
Alice’s Journey Begins
Alice was bored one day and decided

License

The model inherits the original MIT license from inclusionAI/Ling-3.0-tiny-base-midtrain.

Downloads last month: 507

GGUF

Model size

8B params

Architecture

bailingmoe3

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for FriskyFennec/Ling-3.0-tiny-base-midtrain-GGUF

Base model

inclusionAI/Ling-3.0-tiny-base-midtrain

Quantized

(2)

this model