Text Generation
MLX
Safetensors
English
small-language-model
from-scratch
conversational
apple-silicon
research
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 scripts/verify_package.py from OpenSML/Solstice-1: direct link, hf CLI and curl.
- Browser
- Download file 1.76 kB
-
https://huggingface.co/OpenSML/Solstice-1/resolve/main/scripts/verify_package.py
- Command line
-
hf download hf://OpenSML/Solstice-1/scripts/verify_package.py
-
curl -L -o verify_package.py https://huggingface.co/OpenSML/Solstice-1/resolve/main/scripts/verify_package.py
1.76 kB
| #!/usr/bin/env python3 | |
| """Verify release files without loading the model or accessing the network.""" | |
| import argparse | |
| import hashlib | |
| import json | |
| from pathlib import Path | |
| ROOT = Path(__file__).resolve().parents[1] | |
| def digest(path): | |
| with path.open('rb') as stream: | |
| return hashlib.file_digest(stream, 'sha256').hexdigest() | |
| def main(): | |
| parser = argparse.ArgumentParser(description=__doc__) | |
| parser.add_argument('--source-only', action='store_true', help='Allow the GitHub checkout to omit model.safetensors.') | |
| args = parser.parse_args() | |
| files = json.loads((ROOT/'FILE_MANIFEST.json').read_text())['files'] | |
| failures = [] | |
| checked = 0 | |
| for name, record in files.items(): | |
| path = (ROOT/name).resolve() | |
| if not path.is_relative_to(ROOT) or not path.is_file(): | |
| failures.append(f'Missing or invalid path: {name}') | |
| elif path.stat().st_size != record['bytes'] or digest(path) != record['sha256']: | |
| failures.append(f'Integrity mismatch: {name}') | |
| else: | |
| checked += 1 | |
| weights = ROOT/'model.safetensors' | |
| if weights.is_file(): | |
| expected = json.loads((ROOT/'config.json').read_text())['weight_sha256'] | |
| if 'model.safetensors' not in files: | |
| if digest(weights) != expected: | |
| failures.append('Weight checksum does not match config.json') | |
| else: | |
| checked += 1 | |
| elif not args.source_only: | |
| failures.append('Missing model.safetensors; download it from OpenSML/Solstice-1.') | |
| print(json.dumps({'passed': not failures, 'files_verified': checked, 'weights_present': weights.is_file(), 'failures': failures}, indent=2)) | |
| raise SystemExit(bool(failures)) | |
| if __name__ == '__main__': | |
| main() | |