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 BACKUP_AND_CLEANUP.md from OpenSML/Solstice-1: direct link, hf CLI and curl.
- Browser
- Download file 730 Bytes
-
https://huggingface.co/OpenSML/Solstice-1/resolve/main/BACKUP_AND_CLEANUP.md
- Command line
-
hf download hf://OpenSML/Solstice-1/BACKUP_AND_CLEANUP.md
-
curl -L -o BACKUP_AND_CLEANUP.md https://huggingface.co/OpenSML/Solstice-1/resolve/main/BACKUP_AND_CLEANUP.md
Preservation and cleanup
The selected checkpoint is stage-3 update 128. The inference export hash and ancestor identities are recorded in provenance/LINEAGE.json. Existing pretrained masters, parent 2000, parent 1800, prior attempt-5 checkpoints and checkpoint 167 remain protected locally; preparing this release does not delete or modify them.
The GitHub source repository excludes the large merged weight tensor. Hugging Face holds the inference weight artifact. Verify both package manifests and load the independently downloaded artifact before treating a public upload as complete. Retain local originals until that verification has succeeded. Optimizer state and raw corpora are not backed up by the inference release.