Instructions to use SakanaAI/TinySwallow-1.5B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SakanaAI/TinySwallow-1.5B-Instruct-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="SakanaAI/TinySwallow-1.5B-Instruct-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SakanaAI/TinySwallow-1.5B-Instruct-GGUF", dtype="auto")

llama-cpp-python

How to use SakanaAI/TinySwallow-1.5B-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="SakanaAI/TinySwallow-1.5B-Instruct-GGUF",
	filename="tinyswallow-1.5b-instruct-q5_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use SakanaAI/TinySwallow-1.5B-Instruct-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SakanaAI/TinySwallow-1.5B-Instruct-GGUF:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf SakanaAI/TinySwallow-1.5B-Instruct-GGUF:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SakanaAI/TinySwallow-1.5B-Instruct-GGUF:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf SakanaAI/TinySwallow-1.5B-Instruct-GGUF:Q5_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 SakanaAI/TinySwallow-1.5B-Instruct-GGUF:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf SakanaAI/TinySwallow-1.5B-Instruct-GGUF:Q5_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 SakanaAI/TinySwallow-1.5B-Instruct-GGUF:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SakanaAI/TinySwallow-1.5B-Instruct-GGUF:Q5_K_M

Use Docker

docker model run hf.co/SakanaAI/TinySwallow-1.5B-Instruct-GGUF:Q5_K_M

LM Studio
Jan

vLLM

How to use SakanaAI/TinySwallow-1.5B-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SakanaAI/TinySwallow-1.5B-Instruct-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": "SakanaAI/TinySwallow-1.5B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SakanaAI/TinySwallow-1.5B-Instruct-GGUF:Q5_K_M

SGLang

How to use SakanaAI/TinySwallow-1.5B-Instruct-GGUF 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 "SakanaAI/TinySwallow-1.5B-Instruct-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SakanaAI/TinySwallow-1.5B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "SakanaAI/TinySwallow-1.5B-Instruct-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SakanaAI/TinySwallow-1.5B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use SakanaAI/TinySwallow-1.5B-Instruct-GGUF with Ollama:
```
ollama run hf.co/SakanaAI/TinySwallow-1.5B-Instruct-GGUF:Q5_K_M
```

Unsloth Studio new

How to use SakanaAI/TinySwallow-1.5B-Instruct-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 SakanaAI/TinySwallow-1.5B-Instruct-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 SakanaAI/TinySwallow-1.5B-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SakanaAI/TinySwallow-1.5B-Instruct-GGUF to start chatting

Pi new

How to use SakanaAI/TinySwallow-1.5B-Instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf SakanaAI/TinySwallow-1.5B-Instruct-GGUF:Q5_K_M

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": "SakanaAI/TinySwallow-1.5B-Instruct-GGUF:Q5_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use SakanaAI/TinySwallow-1.5B-Instruct-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf SakanaAI/TinySwallow-1.5B-Instruct-GGUF:Q5_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 SakanaAI/TinySwallow-1.5B-Instruct-GGUF:Q5_K_M

Run Hermes

hermes

Docker Model Runner
How to use SakanaAI/TinySwallow-1.5B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/SakanaAI/TinySwallow-1.5B-Instruct-GGUF:Q5_K_M
```

Lemonade

How to use SakanaAI/TinySwallow-1.5B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SakanaAI/TinySwallow-1.5B-Instruct-GGUF:Q5_K_M

Run and chat with the model

lemonade run user.TinySwallow-1.5B-Instruct-GGUF-Q5_K_M

List all available models

lemonade list

TinySwallow-1.5B-Instruct-GGUF

🤗 Models | 📚 Paper | 📝 Blog | 🐦 Twitter

This is the TinySwallow-1.5B-Instruct model in GGUF format.

TinySwallow-1.5B-Instruct is an instruction-tuned version of TinySwallow-1.5B, created through TAID (Temporally Adaptive Interpolated Distillation), our new knowledge distillation method. We used Qwen2.5-32B-Instruct as the teacher model and Qwen2.5-1.5B-Instruct as the student model. The model has been further instruction-tuned to enhance its ability to follow instructions and engage in conversations in Japanese.

Usage

Check out our GitHub repository to quickly run it on your iPhone.

Model Details

Model type: Autoregressive Language Model
Language(s): Japanese
Paper: http://arxiv.org/abs/2501.16937
Blog: https://sakana.ai/taid-jp/
Training Datasets:

Uses

This model is provided for research and development purposes only and should be considered as an experimental prototype. It is not intended for commercial use or deployment in mission-critical environments. Use of this model is at the user's own risk, and its performance and outcomes are not guaranteed. Sakana AI shall not be liable for any direct, indirect, special, incidental, or consequential damages, or any loss arising from the use of this model, regardless of the results obtained. Users must fully understand the risks associated with the use of this model and use it at their own discretion.

Acknowledgement

We would like to thank the developers of the source models for their contributions and for making their work available.

Authors

License

This model is derived from Qwen (Apache 2.0) and trained on Gemma data (Gemma Terms, Prohibited Use). Use (including commercial) is permitted if you comply with both licenses/policies above.

Citation

@misc{sakana2025taid,
      title         = {TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models}, 
      author.       = {Makoto Shing and Kou Misaki and Han Bao and Sho Yokoi and Takuya Akiba},
      year          = {2025},
      eprint        = {2501.16937},
      archivePrefix = {arXiv},
      primaryClass  = {cs.LG},
      url           = {http://arxiv.org/abs/2501.16937}
}