Instructions to use paulo037/stable-code-instruct-3b-spider-1500-steps-Q4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use paulo037/stable-code-instruct-3b-spider-1500-steps-Q4 with Transformers:

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

pipe = pipeline("text-generation", model="paulo037/stable-code-instruct-3b-spider-1500-steps-Q4")

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

tokenizer = AutoTokenizer.from_pretrained("paulo037/stable-code-instruct-3b-spider-1500-steps-Q4")
model = AutoModelForCausalLM.from_pretrained("paulo037/stable-code-instruct-3b-spider-1500-steps-Q4", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use paulo037/stable-code-instruct-3b-spider-1500-steps-Q4 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 paulo037/stable-code-instruct-3b-spider-1500-steps-Q4
# Run inference directly in the terminal:
llama cli -hf paulo037/stable-code-instruct-3b-spider-1500-steps-Q4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf paulo037/stable-code-instruct-3b-spider-1500-steps-Q4
# Run inference directly in the terminal:
llama cli -hf paulo037/stable-code-instruct-3b-spider-1500-steps-Q4

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 paulo037/stable-code-instruct-3b-spider-1500-steps-Q4
# Run inference directly in the terminal:
./llama-cli -hf paulo037/stable-code-instruct-3b-spider-1500-steps-Q4

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 paulo037/stable-code-instruct-3b-spider-1500-steps-Q4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf paulo037/stable-code-instruct-3b-spider-1500-steps-Q4

Use Docker

docker model run hf.co/paulo037/stable-code-instruct-3b-spider-1500-steps-Q4

LM Studio
Jan

vLLM

How to use paulo037/stable-code-instruct-3b-spider-1500-steps-Q4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "paulo037/stable-code-instruct-3b-spider-1500-steps-Q4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "paulo037/stable-code-instruct-3b-spider-1500-steps-Q4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/paulo037/stable-code-instruct-3b-spider-1500-steps-Q4

SGLang

How to use paulo037/stable-code-instruct-3b-spider-1500-steps-Q4 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 "paulo037/stable-code-instruct-3b-spider-1500-steps-Q4" \
    --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": "paulo037/stable-code-instruct-3b-spider-1500-steps-Q4",
		"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 "paulo037/stable-code-instruct-3b-spider-1500-steps-Q4" \
        --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": "paulo037/stable-code-instruct-3b-spider-1500-steps-Q4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use paulo037/stable-code-instruct-3b-spider-1500-steps-Q4 with Ollama:
```
ollama run hf.co/paulo037/stable-code-instruct-3b-spider-1500-steps-Q4
```
Unsloth Desktop
Docker Model Runner
How to use paulo037/stable-code-instruct-3b-spider-1500-steps-Q4 with Docker Model Runner:
```
docker model run hf.co/paulo037/stable-code-instruct-3b-spider-1500-steps-Q4
```

Lemonade

How to use paulo037/stable-code-instruct-3b-spider-1500-steps-Q4 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull paulo037/stable-code-instruct-3b-spider-1500-steps-Q4

Run and chat with the model

lemonade run user.stable-code-instruct-3b-spider-1500-steps-Q4-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

No model card

Downloads last month: 40

GGUF

Model size

3B params

Architecture

stablelm

Hardware compatibility

We're not able to determine the quantization variants.

View +1 variant