Instructions to use nisten/Biggie-SmoLlm-0.4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nisten/Biggie-SmoLlm-0.4B with Transformers:

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

pipe = pipeline("text-generation", model="nisten/Biggie-SmoLlm-0.4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nisten/Biggie-SmoLlm-0.4B")
model = AutoModelForCausalLM.from_pretrained("nisten/Biggie-SmoLlm-0.4B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use nisten/Biggie-SmoLlm-0.4B 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 nisten/Biggie-SmoLlm-0.4B:Q8_0
# Run inference directly in the terminal:
llama cli -hf nisten/Biggie-SmoLlm-0.4B:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf nisten/Biggie-SmoLlm-0.4B:Q8_0
# Run inference directly in the terminal:
llama cli -hf nisten/Biggie-SmoLlm-0.4B:Q8_0

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 nisten/Biggie-SmoLlm-0.4B:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf nisten/Biggie-SmoLlm-0.4B:Q8_0

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 nisten/Biggie-SmoLlm-0.4B:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nisten/Biggie-SmoLlm-0.4B:Q8_0

Use Docker

docker model run hf.co/nisten/Biggie-SmoLlm-0.4B:Q8_0

LM Studio
Jan

vLLM

How to use nisten/Biggie-SmoLlm-0.4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nisten/Biggie-SmoLlm-0.4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nisten/Biggie-SmoLlm-0.4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nisten/Biggie-SmoLlm-0.4B:Q8_0

SGLang

How to use nisten/Biggie-SmoLlm-0.4B 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 "nisten/Biggie-SmoLlm-0.4B" \
    --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": "nisten/Biggie-SmoLlm-0.4B",
		"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 "nisten/Biggie-SmoLlm-0.4B" \
        --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": "nisten/Biggie-SmoLlm-0.4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use nisten/Biggie-SmoLlm-0.4B with Ollama:
```
ollama run hf.co/nisten/Biggie-SmoLlm-0.4B:Q8_0
```
Unsloth Desktop
Docker Model Runner
How to use nisten/Biggie-SmoLlm-0.4B with Docker Model Runner:
```
docker model run hf.co/nisten/Biggie-SmoLlm-0.4B:Q8_0
```

Lemonade

How to use nisten/Biggie-SmoLlm-0.4B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nisten/Biggie-SmoLlm-0.4B:Q8_0

Run and chat with the model

lemonade run user.Biggie-SmoLlm-0.4B-Q8_0

List all available models

lemonade list

Atomic Chat

###Coherent Frankenstein of smolLm-0.36b upped to 0.4b

This took about 5 hours of semi-automated continuous merging to figure out the recipe. Model is smarter, and UNTRAINED. Uploaded it for training. Yet it performs well as is even quantized to 8bit. 8bit gguf included for testing.

wget https://huggingface.co/nisten/Biggie-SmoLlm-0.4B/resolve/main/Biggie_SmolLM_400M_q8_0.gguf

./llama-cli -ngl 99 -co --temp 0 -p "How to build a city on Mars via calculating Aldrin-Cycler orbits?" -m Biggie_SmolLM_400M_q8_0.gguf -cnv -fa --keep -1