Instructions to use seanpoyner/smolcode-coder-bsd-3b-tools with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use seanpoyner/smolcode-coder-bsd-3b-tools with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="seanpoyner/smolcode-coder-bsd-3b-tools",
	filename="smolcode-coder-bsd-3b-q4_k_m.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use seanpoyner/smolcode-coder-bsd-3b-tools with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf seanpoyner/smolcode-coder-bsd-3b-tools:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf seanpoyner/smolcode-coder-bsd-3b-tools:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf seanpoyner/smolcode-coder-bsd-3b-tools:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf seanpoyner/smolcode-coder-bsd-3b-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 seanpoyner/smolcode-coder-bsd-3b-tools:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf seanpoyner/smolcode-coder-bsd-3b-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 seanpoyner/smolcode-coder-bsd-3b-tools:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf seanpoyner/smolcode-coder-bsd-3b-tools:Q4_K_M

Use Docker

docker model run hf.co/seanpoyner/smolcode-coder-bsd-3b-tools:Q4_K_M

LM Studio
Jan

vLLM

How to use seanpoyner/smolcode-coder-bsd-3b-tools with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "seanpoyner/smolcode-coder-bsd-3b-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": "seanpoyner/smolcode-coder-bsd-3b-tools",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/seanpoyner/smolcode-coder-bsd-3b-tools:Q4_K_M

Ollama
How to use seanpoyner/smolcode-coder-bsd-3b-tools with Ollama:
```
ollama run hf.co/seanpoyner/smolcode-coder-bsd-3b-tools:Q4_K_M
```

Unsloth Studio

How to use seanpoyner/smolcode-coder-bsd-3b-tools 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 seanpoyner/smolcode-coder-bsd-3b-tools 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 seanpoyner/smolcode-coder-bsd-3b-tools to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for seanpoyner/smolcode-coder-bsd-3b-tools to start chatting

How to use seanpoyner/smolcode-coder-bsd-3b-tools with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf seanpoyner/smolcode-coder-bsd-3b-tools:Q4_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": "seanpoyner/smolcode-coder-bsd-3b-tools:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use seanpoyner/smolcode-coder-bsd-3b-tools with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf seanpoyner/smolcode-coder-bsd-3b-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 seanpoyner/smolcode-coder-bsd-3b-tools:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use seanpoyner/smolcode-coder-bsd-3b-tools with Docker Model Runner:
```
docker model run hf.co/seanpoyner/smolcode-coder-bsd-3b-tools:Q4_K_M
```

Lemonade

How to use seanpoyner/smolcode-coder-bsd-3b-tools with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull seanpoyner/smolcode-coder-bsd-3b-tools:Q4_K_M

Run and chat with the model

lemonade run user.smolcode-coder-bsd-3b-tools-Q4_K_M

List all available models

lemonade list

smolcode-coder-1.5b-tools

A LoRA fine-tune of Qwen2.5-Coder-1.5B-Instruct that teaches the model to emit native <tool_call> function calls, so a 1.5B coder model can actually drive an agentic write → run → fix → verify loop.

Built for smolcode — an SLM-optimized agentic coding assistant — for the Hugging Face Build Small hackathon.

Why

Out of the box, small Qwen-Coder models describe tool calls as plain-text/```json instead of emitting the native <tool_call> token (id 151657) that runtimes (Ollama, llama.cpp) parse into OpenAI-style tool_calls — which breaks agentic loops. This fine-tune closes that gap on a tiny (1.5B) model: 100% native <tool_call> emission in free generation on held-out prompts (base model: 0%).

Results

Native tool-call rate: 100% (16/16 held-out prompts) — the release gate.
Agentic bench (smolcode pass@1, 10 tasks): 9/10 as the entry tier of a 1.5B→8B→30B ladder, solving 7/10 entirely on its own (2–16s each). For comparison the all-Granite ladder (3B entry) scores 10/10 — the 1.5B carries the same standalone load as a 2×-larger 3B.
Train loss: 0.138 (3 epochs, assistant-only loss).

Training

Base: Qwen/Qwen2.5-Coder-1.5B-Instruct
Method: bf16 LoRA (r=16, α=32) on attention + MLP projections, plus full training of embed_tokens + lm_head (modules_to_save) — required so the model can output the <tool_call> special token, which LoRA on attention/MLP alone cannot. Assistant-only loss (loss on tool calls + final answers only).
Data: NousResearch/hermes-function-calling-v1 (breadth) + synthetic smolcode tool-use trajectories (sharpness), all rendered through the same apply_chat_template(tools=...) used at inference — training target is byte-identical to the served prompt (fixes the v1 train/inference template mismatch).
Schedule: 3 epochs, full 2048 sequence length. Trained on Modal (A100).

Serving — read this, two non-obvious requirements

Serve via the GGUF, not the safetensors directly. Ollama's bf16-safetensors auto-import produces garbage (??????) for this model. Use the included smolcode-1.5b-q4_k_m.gguf (converted with llama.cpp convert_hf_to_gguf.py):
```
ollama create smolcode-coder-1.5b:tools -f Modelfile   # Modelfile is in this repo
```
repeat_penalty / repetition_penalty MUST be 1.0. The tool system prompt literally contains the <tool_call> token, so any penalty > 1 suppresses the model from emitting it (you'll see a stray token + bare JSON instead). The included Modelfile sets PARAMETER repeat_penalty 1.0. For raw transformers.generate, pass repetition_penalty=1.0.

With those, Ollama's /v1/chat/completions returns proper native tool_calls.

Use (transformers)

Standard Qwen2.5 chat template with tools=; greedy, repetition_penalty=1.0. The model responds with <tool_call>{"name": ..., "arguments": ...}</tool_call>.

Files

model.safetensors + tokenizer/config — the merged model (lm_head untied).
smolcode-1.5b-q4_k_m.gguf — quantized GGUF for serving.
Modelfile — Ollama import recipe (template + repeat_penalty 1.0).

License

Apache-2.0 (inherits from the base model).

Downloads last month: 17

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for seanpoyner/smolcode-coder-bsd-3b-tools

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-Coder-1.5B

Finetuned

Qwen/Qwen2.5-Coder-1.5B-Instruct

Quantized

(134)

this model

seanpoyner
/

smolcode-coder-bsd-3b-tools