Instructions to use philipjohnbasile/wisp-coder-110m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use philipjohnbasile/wisp-coder-110m with Transformers:

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

pipe = pipeline("text-generation", model="philipjohnbasile/wisp-coder-110m")

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

tokenizer = AutoTokenizer.from_pretrained("philipjohnbasile/wisp-coder-110m")
model = AutoModelForCausalLM.from_pretrained("philipjohnbasile/wisp-coder-110m", device_map="auto")

MLX

How to use philipjohnbasile/wisp-coder-110m with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm
# if on a CUDA device, also pip install mlx[cuda]

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("philipjohnbasile/wisp-coder-110m")

prompt = "Once upon a time in"
text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use philipjohnbasile/wisp-coder-110m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "philipjohnbasile/wisp-coder-110m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "philipjohnbasile/wisp-coder-110m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/philipjohnbasile/wisp-coder-110m

SGLang

How to use philipjohnbasile/wisp-coder-110m 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 "philipjohnbasile/wisp-coder-110m" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "philipjohnbasile/wisp-coder-110m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "philipjohnbasile/wisp-coder-110m" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "philipjohnbasile/wisp-coder-110m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

MLX LM

How to use philipjohnbasile/wisp-coder-110m with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Generate some text
mlx_lm.generate --model "philipjohnbasile/wisp-coder-110m" --prompt "Once upon a time"

Docker Model Runner
How to use philipjohnbasile/wisp-coder-110m with Docker Model Runner:
```
docker model run hf.co/philipjohnbasile/wisp-coder-110m
```
Atomic Chat

wisp-coder-110m / assets /ARTWORK.md

philipjohnbasile

Bring the Wisp garden identity to the model card

b8df715 verified about 2 months ago

preview code

Raw History Blame Contribute Delete

2.12 kB

Wisp model card artwork

This card reuses the original transparent wildflower illustration created for the Wisp Coder demo. The artwork is AI-generated, inspired by the user-provided Michael De Feo / The Flower Guy reference. It is not the artist's work or an endorsement.

The image is displayed in full using natural proportions; no flowers are cropped. The model card uses text and HTML layout rather than embedding technical content in an image.

Source

https://huggingface.co/spaces/philipjohnbasile/wisp-coder-demo

wisp-wildflowers.png is the final 1536×1024 RGBA hero and footer illustration, generated with the same built-in tool. Its alpha channel was verified; roughly 44% of its pixels are fully transparent.

Generation prompt

Create a new original editorial artwork for an expressive code playground website. Inspired by Michael De Feo / The Flower Guy's layered, gestural floral interventions. Landscape 1536x1024, REAL TRANSPARENT background (alpha), no canvas rectangle, no text, no letters, no signature, no frame, no people. Airy asymmetrical cloud of large and small painted flowers and winding stems, concentrated on the right two thirds, drifting down into lower left, with generous transparent spaces between stems. Loose flat five- and six-petal forms, interrupted looping outlines and quickly daubed irregular petals; raw acrylic, gouache and oil-stick marks with thin paint drips. More abstract and graphic than realistic botanical illustration. Hot coral and pink, ultramarine, rich emerald, acid yellow touches, powder blue and deep wine. Some outlined flowers with transparent interiors, some thickly painted solid petals, lively mismatched scales. Rough playful hand-painted energy, complex layered marks but a legible open silhouette at website size. It should feel like paint blooming across the website's underlying paper and typography, not a bouquet in a vase, not a greeting card, not a stock watercolor illustration. Transparent background throughout the negative space. Make the outer edges organic, with sparse little painted marks extending beyond the main flowers.