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
Commit History
2 days ago
-
Publish main JSONLite checkpoint and verified evaluation package
Verified signatureMain model weights, native inference package, one-SFT training lineage and evaluation evidence.319dca0 -
Clarify intended use and verified JSON limitations
Verified signatureSynchronize the plain-language scope, technical report, run guide, source archive and checksums with the official model repository. Model weights and generation behavior are unchanged.3e9c0aa
6 days ago
-
Group each usage example with its instruction, text, schema and output
Verified signature0f9ac9b -
Label prompt instruction and wrap its text for readability
Verified signature9f83ad0 -
Present released model metrics without release comparisons
Verified signature2caca97 -
Update main model with joint JSON extraction SFT and verified results
Verified signature6debcfe
7 days ago
-
Update main checkpoint with focused extraction SFT and verified results
Verified signaturePublish the verified main JSONLite weights, native JSON runtime, four checked examples, complete training lineage and matched evaluation. Preserve the public model name and prior immutable release history.7a4a2b0
8 days ago
-
Add four verified source/schema/JSON interaction examples
Verified signaturee7ab959 -
Replace JSONLite with native source-schema JSON model and verified SFT results
Verified signatureUpdate selected weights to the native JSON continuation; ship the matching raw-output runner, tokenizer/configuration, complete training lineage, SFT data/settings, held-out and playground results, examples, verification records and checksums. One whole-object generation with no fieldwise assembly or repair.96ec8c0 -
Add pretraining training-loss and held-out validation figure
Verified signaturec28d60c -
Link JSONLite to OpenSML-Base-175M pretrained parent
Verified signature3f1f942 -
Add selected BF16 model weights, tokenizer and offline inference runner
Verified signaturec798f8d -
Remove preparation status and unnecessary repository references
Verified signaturea445852 -
Use JSONLite Instruct model name in the model card
Verified signature6b4ad92 -
Add JSONLite model card and verified inference documentation
Verified signaturef8ffffe