Instructions to use OpenSML/Solstice-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use OpenSML/Solstice-1 with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("OpenSML/Solstice-1") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use OpenSML/Solstice-1 with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "OpenSML/Solstice-1"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "OpenSML/Solstice-1" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OpenSML/Solstice-1", "messages": [ {"role": "user", "content": "Hello"} ] }' - Atomic Chat
Download SOURCE_NOTICE.md from OpenSML/Solstice-1: direct link, hf CLI and curl.
- Browser
- Download file 1.05 kB
-
https://huggingface.co/OpenSML/Solstice-1/resolve/main/SOURCE_NOTICE.md
- Command line
-
hf download hf://OpenSML/Solstice-1/SOURCE_NOTICE.md
-
curl -L -o SOURCE_NOTICE.md https://huggingface.co/OpenSML/Solstice-1/resolve/main/SOURCE_NOTICE.md
Source and model notice
Copyright 2026 William Zebrowski.
The selected Solstice-1 model weights, frozen tokenizer artifacts to the extent controlled by the author, and author-controlled project code/documentation are released under Apache License 2.0. See LICENSE. This is the author's explicit release decision for Solstice-1, rather than an inferred license from earlier OpenSML releases.
Third-party software and training materials retain their own licenses and attribution. Apache-2.0 does not relicense upstream datasets, their underlying documents/code repositories, or separately licensed vendored components. Raw training datasets are not redistributed here. See THIRD_PARTY_NOTICES.md and docs/DATA.md.
The native model implementation and tokenizer originate in the owner's OpenSML MLX research workspace. Original source hashes, exact inference weight identity and sanitized archival hashes are included. Examples and verification outputs describe this specific selected checkpoint; they are not guarantees of general accuracy or safety.