Instructions to use ggml-org/stories15M_MOE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ggml-org/stories15M_MOE with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ggml-org/stories15M_MOE")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ggml-org/stories15M_MOE")
model = AutoModelForCausalLM.from_pretrained("ggml-org/stories15M_MOE")

llama-cpp-python

How to use ggml-org/stories15M_MOE with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ggml-org/stories15M_MOE",
	filename="moe_shakespeare15M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ggml-org/stories15M_MOE with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ggml-org/stories15M_MOE:F16
# Run inference directly in the terminal:
llama-cli -hf ggml-org/stories15M_MOE:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ggml-org/stories15M_MOE:F16
# Run inference directly in the terminal:
llama-cli -hf ggml-org/stories15M_MOE: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 ggml-org/stories15M_MOE:F16
# Run inference directly in the terminal:
./llama-cli -hf ggml-org/stories15M_MOE: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 ggml-org/stories15M_MOE:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ggml-org/stories15M_MOE:F16

Use Docker

docker model run hf.co/ggml-org/stories15M_MOE:F16

LM Studio
Jan

vLLM

How to use ggml-org/stories15M_MOE with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ggml-org/stories15M_MOE"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ggml-org/stories15M_MOE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ggml-org/stories15M_MOE:F16

SGLang

How to use ggml-org/stories15M_MOE with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ggml-org/stories15M_MOE" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ggml-org/stories15M_MOE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ggml-org/stories15M_MOE" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ggml-org/stories15M_MOE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use ggml-org/stories15M_MOE with Ollama:
```
ollama run hf.co/ggml-org/stories15M_MOE:F16
```

Unsloth Studio

How to use ggml-org/stories15M_MOE 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 ggml-org/stories15M_MOE 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 ggml-org/stories15M_MOE to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ggml-org/stories15M_MOE to start chatting

Docker Model Runner
How to use ggml-org/stories15M_MOE with Docker Model Runner:
```
docker model run hf.co/ggml-org/stories15M_MOE:F16
```

Lemonade

How to use ggml-org/stories15M_MOE with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ggml-org/stories15M_MOE:F16

Run and chat with the model

lemonade run user.stories15M_MOE-F16

List all available models

lemonade list

stories15M_MOE

This model is ModelCloud/tinyllama-15M-stories repeated 4 times to make 4 experts.

The model is used for testing, not intended to be used in production (unless your product is some kind of bedtime story teller)

Weight of router is initialized randomly

shakespeare LoRA adapter

A LoRA adapter trained on first 100 paragraphs of shakespeare can be found inside moe_shakespeare15M

With input: Look in thy glass

Original model generates: Look in thy glass was a little girl. She was only three years old and she was three years old. She was
LoRA adapter generates: Look in thy glass in love of the eye: That's when when the eye see thy on the sun'

Downloads last month: 116,231

Safetensors

Model size

36.4M params

Tensor type

F32

F16

ggml-org
/

stories15M_MOE

stories15M_MOE

shakespeare LoRA adapter

Spaces using ggml-org/stories15M_MOE 5