Text Generation
MLX
Safetensors
English
information-extraction
structured-output
json
small-language-model
apple-silicon
from-scratch
post-training
research
Instructions to use OpenSML/OpenSML-JSONLite-175M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use OpenSML/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("OpenSML/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 OpenSML/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 "OpenSML/OpenSML-JSONLite-175M" --prompt "Once upon a time"
- Atomic Chat
Commit History
6 days ago
-
Publish main JSONLite checkpoint and verified evaluation package
Verified signatureMain model weights, native inference package, one-SFT training lineage, evaluation records and intended-use documentation.ab95dde -
Clarify intended use and verified JSON limitations
Verified signatureAdd a plain-language scope section before usage examples and detailed limitations beside evaluation results. Synchronize the run guide, source archive and checksums. Model weights, tokenizer and native inference algorithm are unchanged.8f5e19c
10 days ago
-
Update main model with joint JSON extraction SFT and verified results
Verified signaturePublish the verified main checkpoint, unchanged tokenizer, native runtime bundle and updated source/schema/output examples. Original observed 1,444-request evaluation: 1,271 correct, 94.17% field accuracy, 92.88% value F1; 24 individual regressions documented. No JSON assembly, repair or constrained decoding. Previous revisions remain available.56c4fe4
11 days ago
-
Update main checkpoint with focused extraction SFT and verified results
Verified signaturePublish complete verified main weights and native inference package. Add continuation lineage, matched results and four checked examples; retain the existing public model name and release history.c00cb36
12 days ago
-
Upload complete native JSON model, runtime and verified examples
Verified signatureNative source-text + JSON Schema generation weights, tokenizer, MLX runtime, training report, evaluation evidence, checksums and four verified playground examples.f9d319a