Instructions to use schangg/sprite-100m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use schangg/sprite-100m 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 schangg/sprite-100m:Q8_0
# Run inference directly in the terminal:
llama cli -hf schangg/sprite-100m:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf schangg/sprite-100m:Q8_0
# Run inference directly in the terminal:
llama cli -hf schangg/sprite-100m: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 schangg/sprite-100m:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf schangg/sprite-100m: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 schangg/sprite-100m:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf schangg/sprite-100m:Q8_0

Use Docker

docker model run hf.co/schangg/sprite-100m:Q8_0

LM Studio
Jan

vLLM

How to use schangg/sprite-100m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "schangg/sprite-100m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "schangg/sprite-100m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/schangg/sprite-100m:Q8_0

Ollama
How to use schangg/sprite-100m with Ollama:
```
ollama run hf.co/schangg/sprite-100m:Q8_0
```

Unsloth Studio

How to use schangg/sprite-100m 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 schangg/sprite-100m 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 schangg/sprite-100m to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for schangg/sprite-100m to start chatting

Docker Model Runner
How to use schangg/sprite-100m with Docker Model Runner:
```
docker model run hf.co/schangg/sprite-100m:Q8_0
```

Lemonade

How to use schangg/sprite-100m with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull schangg/sprite-100m:Q8_0

Run and chat with the model

lemonade run user.sprite-100m-Q8_0

List all available models

lemonade list

Atomic Chat

sprite-100m / README.md

schangg

Update README.md

03a835b verified about 8 hours ago

preview code

Raw

History Blame Contribute Delete

439 Bytes

metadata

license: mit
datasets:
  - bigcode/the-stack-v2-train-full-ids
  - bigcode/starcoderdata
language:
  - en
pipeline_tag: text-generation
tags:
  - coding
  - full-line
  - quantized
  - local
description: >-
  a 100m param full line code completion model trained from scratch for C++ and
  Metal. 41% perfect line rate and 150 ms debounce time on M4 Air, replicates
  performance of JetBrain's proprietary 100m FLCC model. Trained in 48 hours on
  1 H100