Text Generation
MLX
Safetensors
English
information-extraction
structured-output
json
small-language-model
apple-silicon
from-scratch
post-training
research
Instructions to use wzebrowski/OpenSML-JSONLite-175M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use wzebrowski/OpenSML-JSONLite-175M 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("wzebrowski/OpenSML-JSONLite-175M") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use wzebrowski/OpenSML-JSONLite-175M with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "wzebrowski/OpenSML-JSONLite-175M" --prompt "Once upon a time"
- Atomic Chat
Download CITATION.cff from wzebrowski/OpenSML-JSONLite-175M: direct link, hf CLI and curl.
- Browser
- Download file 689 Bytes
-
https://huggingface.co/wzebrowski/OpenSML-JSONLite-175M/resolve/main/CITATION.cff
- Command line
-
hf download hf://wzebrowski/OpenSML-JSONLite-175M/CITATION.cff
-
curl -L -o CITATION.cff https://huggingface.co/wzebrowski/OpenSML-JSONLite-175M/resolve/main/CITATION.cff
689 Bytes
| cff-version: 1.2.0 | |
| message: "Please cite this source repository and the selected checkpoint and native inference identity when reporting OpenSML-JSONLite-175M." | |
| title: "OpenSML-JSONLite-175M: Native JSON Generation from Source Text and Schema" | |
| authors: | |
| - family-names: Zebrowski | |
| given-names: William | |
| version: 0.4.0 | |
| date-released: 2026-10-16 | |
| url: "https://github.com/williamzebrowskI/OpenSML-JSONLite-175M" | |
| repository-code: "https://github.com/williamzebrowskI/OpenSML-JSONLite-175M" | |
| license: Apache-2.0 | |
| abstract: "Source, tokenizer, training provenance and observed evaluation records for a 175.6M-parameter native text-to-JSON model. Source license only; weights are not included." | |