Instructions to use rdubwiley/SmolLM3-3B-distilled-py-tools with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rdubwiley/SmolLM3-3B-distilled-py-tools with Transformers:

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

pipe = pipeline("text-generation", model="rdubwiley/SmolLM3-3B-distilled-py-tools")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rdubwiley/SmolLM3-3B-distilled-py-tools")
model = AutoModelForCausalLM.from_pretrained("rdubwiley/SmolLM3-3B-distilled-py-tools", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use rdubwiley/SmolLM3-3B-distilled-py-tools 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 rdubwiley/SmolLM3-3B-distilled-py-tools:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf rdubwiley/SmolLM3-3B-distilled-py-tools:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf rdubwiley/SmolLM3-3B-distilled-py-tools:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf rdubwiley/SmolLM3-3B-distilled-py-tools: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 rdubwiley/SmolLM3-3B-distilled-py-tools:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf rdubwiley/SmolLM3-3B-distilled-py-tools: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 rdubwiley/SmolLM3-3B-distilled-py-tools:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf rdubwiley/SmolLM3-3B-distilled-py-tools:Q4_K_M

Use Docker

docker model run hf.co/rdubwiley/SmolLM3-3B-distilled-py-tools:Q4_K_M

LM Studio
Jan

vLLM

How to use rdubwiley/SmolLM3-3B-distilled-py-tools with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rdubwiley/SmolLM3-3B-distilled-py-tools"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rdubwiley/SmolLM3-3B-distilled-py-tools",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rdubwiley/SmolLM3-3B-distilled-py-tools:Q4_K_M

SGLang

How to use rdubwiley/SmolLM3-3B-distilled-py-tools 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 "rdubwiley/SmolLM3-3B-distilled-py-tools" \
    --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": "rdubwiley/SmolLM3-3B-distilled-py-tools",
		"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 "rdubwiley/SmolLM3-3B-distilled-py-tools" \
        --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": "rdubwiley/SmolLM3-3B-distilled-py-tools",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use rdubwiley/SmolLM3-3B-distilled-py-tools with Ollama:
```
ollama run hf.co/rdubwiley/SmolLM3-3B-distilled-py-tools:Q4_K_M
```
Unsloth Desktop

How to use rdubwiley/SmolLM3-3B-distilled-py-tools with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rdubwiley/SmolLM3-3B-distilled-py-tools: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": "rdubwiley/SmolLM3-3B-distilled-py-tools:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use rdubwiley/SmolLM3-3B-distilled-py-tools with Docker Model Runner:
```
docker model run hf.co/rdubwiley/SmolLM3-3B-distilled-py-tools:Q4_K_M
```

Lemonade

How to use rdubwiley/SmolLM3-3B-distilled-py-tools with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull rdubwiley/SmolLM3-3B-distilled-py-tools:Q4_K_M

Run and chat with the model

lemonade run user.SmolLM3-3B-distilled-py-tools-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use rdubwiley/SmolLM3-3B-distilled-py-tools with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rdubwiley/SmolLM3-3B-distilled-py-tools: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 rdubwiley/SmolLM3-3B-distilled-py-tools:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use rdubwiley/SmolLM3-3B-distilled-py-tools with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rdubwiley/SmolLM3-3B-distilled-py-tools: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 "rdubwiley/SmolLM3-3B-distilled-py-tools: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"

rdubwiley commited on May 8

Commit

37aed62

verified ·

1 Parent(s): 8c494b0

Unsloth Model Card

Browse files

Files changed (1) hide show

README.md +12 -51

README.md CHANGED Viewed

@@ -1,60 +1,21 @@
 ---
 base_model: HuggingFaceTB/SmolLM3-3B
-library_name: transformers
-model_name: SmolLM3-3B-distilled-py-tools
 tags:
-- generated_from_trainer
-- trl
-- sft
-- hf_jobs
 - unsloth
-licence: license
 ---
-# Model Card for SmolLM3-3B-distilled-py-tools
-This model is a fine-tuned version of [HuggingFaceTB/SmolLM3-3B](https://huggingface.co/HuggingFaceTB/SmolLM3-3B).
-It has been trained using [TRL](https://github.com/huggingface/trl).
-## Quick start
-```python
-from transformers import pipeline
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="rdubwiley/SmolLM3-3B-distilled-py-tools", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
-```
-## Training procedure
-This model was trained with SFT.
-### Framework versions
-- TRL: 0.22.2
-- Transformers: 4.57.3
-- Pytorch: 2.10.0
-- Datasets: 4.3.0
-- Tokenizers: 0.22.2
-## Citations
-Cite TRL as:
-```bibtex
-@misc{vonwerra2022trl,
-	title        = {{TRL: Transformer Reinforcement Learning}},
-	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
-	year         = 2020,
-	journal      = {GitHub repository},
-	publisher    = {GitHub},
-	howpublished = {\url{https://github.com/huggingface/trl}}
-}
-```

 ---
 base_model: HuggingFaceTB/SmolLM3-3B
 tags:
+- text-generation-inference
+- transformers
 - unsloth
+- smollm3
+license: apache-2.0
+language:
+- en
 ---
+# Uploaded finetuned  model
+- **Developed by:** rdubwiley
+- **License:** apache-2.0
+- **Finetuned from model :** HuggingFaceTB/SmolLM3-3B
+This smollm3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)